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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18789
    Prev
    Next
    INDEX
    Explanations

    words related to concerns or worries about specific situations or people

    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
    481
    +0.14
    0.7%
    280
    +0.11
    0.5%
    608
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.14
    0.03
    608
    +0.11
    0.03
    280
    +0.11
    0.03
    Negative Logits
    MX
    -0.87
    icol
    -0.74
    DragonMagazine
    -0.72
    Cola
    -0.72
    OGR
    -0.71
    hesis
    -0.70
    orld
    -0.70
    xxxxxxxx
    -0.70
    oun
    -0.70
    Begin
    -0.68
    POSITIVE LOGITS
     losing
    1.07
     preserving
    1.03
     protecting
    1.03
     repercussions
    0.97
     safegu
    0.91
     preventing
    0.91
     getting
    0.91
     whether
    0.91
     privacy
    0.89
     exposing
    0.88
    Activations Density 0.066%

    No Known Activations