© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 16801
    Prev
    Next
    INDEX
    Explanations

    phrases related to raising and discussing questions or concerns, particularly within the context of investigations or reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    185
    +0.11
    0.5%
    51
    +0.10
    0.5%
    86
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.11
    0.03
    51
    +0.10
    0.03
    513
    +0.09
    0.03
    Negative Logits
    nice
    -0.76
    rites
    -0.61
    ellow
    -0.60
    elta
    -0.60
    zig
    -0.59
    ufact
    -0.59
    endars
    -0.58
    eon
    -0.57
     BaseType
    -0.57
     fitt
    -0.57
    POSITIVE LOGITS
     unanswered
    1.25
     whether
    1.06
     arise
    0.92
     concerning
    0.92
     regarding
    0.91
     arises
    0.90
     arising
    0.88
     unresolved
    0.87
     questions
    0.87
     why
    0.86
    Activations Density 0.068%

    No Known Activations