© 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 12288
    9. 8-RES_FS12288-JB
    11. 1449
    Prev
    Next
    INDEX
    Explanations

    phrases related to current circumstances or comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    304
    +0.11
    0.5%
    339
    +0.11
    0.5%
    283
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.11
    0.04
    108
    +0.11
    0.03
    706
    +0.10
    0.04
    Negative Logits
     Parables
    -0.59
     similarity
    -0.59
     Difference
    -0.56
     Byte
    -0.56
     Ammunition
    -0.56
    itialized
    -0.55
     payload
    -0.54
     Digest
    -0.53
    utive
    -0.53
     Mesh
    -0.53
    POSITIVE LOGITS
    adays
    1.67
    here
    1.39
    abouts
    1.03
    heres
    1.02
    lins
    0.83
     defunct
    0.81
    tics
    0.80
    days
    0.76
    terday
    0.75
    ledge
    0.74
    Activations Density 0.095%

    No Known Activations