© 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 EvalsExportsAPI 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. 7666
    Prev
    Next
    INDEX
    Explanations

    phrases related to partnerships, investments, and technological training

    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
    447
    +0.11
    0.5%
    481
    +0.11
    0.5%
    760
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.11
    0.04
    344
    +0.11
    0.05
    93
    +0.10
    0.04
    Negative Logits
    ogenesis
    -0.70
    meal
    -0.69
    amination
    -0.67
    Operation
    -0.66
    tenance
    -0.65
     containment
    -0.65
    inez
    -0.64
    empt
    -0.63
    activation
    -0.62
     phased
    -0.62
    POSITIVE LOGITS
     reputable
    1.28
     talented
    1.23
     esteemed
    1.07
     strangers
    1.05
     illustrious
    1.05
     respected
    1.04
     fellow
    1.01
     eminent
    1.01
     mentors
    1.01
     fellows
    0.98
    Activations Density 0.623%

    No Known Activations