Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 885
    Prev
    Next
    INDEX
    Explanations

    negative or limiting phrases involving actions and outcomes

    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
    5
    +0.13
    0.6%
    482
    +0.10
    0.4%
    668
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.13
    0.05
    383
    +0.10
    0.06
    437
    +0.09
    0.04
    Negative Logits
    cens
    -0.70
     understatement
    -0.68
    uders
    -0.63
    undrum
    -0.62
    opausal
    -0.62
    obo
    -0.62
    geries
    -0.60
    false
    -0.60
    hi
    -0.60
     Hate
    -0.59
    POSITIVE LOGITS
     necessarily
    0.93
    etheless
    0.86
     conclusive
    0.81
    cially
    0.81
     guarantee
    0.69
     infall
    0.69
     specifics
    0.66
     exact
    0.65
     nonetheless
    0.63
     statistically
    0.63
    Activations Density 0.355%

    No Known Activations