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 6144
    5. 8-RES_FS6144-JB
    6. 4538
    Prev
    Next
    INDEX
    Explanations

    references to senior individuals or officials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    711
    +0.13
    0.6%
    167
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.13
    0.03
    21
    +0.10
    0.03
    506
    +0.10
    0.03
    Negative Logits
    pel
    -0.84
    Ĥİ
    -0.69
    fitting
    -0.69
    anism
    -0.69
    adle
    -0.67
    closed
    -0.67
    ibia
    -0.66
    rosso
    -0.66
    gone
    -0.65
    oute
    -0.65
    POSITIVE LOGITS
    ity
    1.05
     citiz
    0.96
    iate
    0.94
     advisor
    0.79
    iates
    0.76
     citizen
    0.76
     adviser
    0.75
    ities
    0.75
     lecturer
    0.74
    ITY
    0.74
    Activations Density 0.125%

    No Known Activations