© 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. 18892
    Prev
    Next
    INDEX
    Explanations

    phrases enclosed in quotation marks

    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
    381
    +0.12
    0.5%
    255
    +0.12
    0.5%
    700
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.03
    381
    +0.12
    0.03
    255
    +0.11
    0.03
    Negative Logits
    Ļ½
    -0.74
    İĭ
    -0.73
    ²¾
    -0.68
    MpServer
    -0.66
    emis
    -0.65
     brill
    -0.60
    psc
    -0.60
    ixture
    -0.59
    ¾
    -0.58
    aser
    -0.58
    POSITIVE LOGITS
    /"
    1.00
     ["
    0.76
     ([
    0.76
     advised
    0.73
     âĢķ
    0.72
    isSpecialOrderable
    0.68
     (*
    0.67
     ("
    0.67
     concludes
    0.67
     implies
    0.67
    Activations Density 0.065%

    No Known Activations