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 3072
    5. 8-RES_FS3072-JB
    6. 1476
    Prev
    Next
    INDEX
    Explanations

    specific types of computer code related to programming languages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    314
    +0.16
    0.7%
    160
    +0.13
    0.6%
    701
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.16
    0.07
    112
    +0.13
    0.06
    314
    +0.11
    0.02
    Negative Logits
    wagen
    -0.70
     regression
    -0.67
     factories
    -0.65
     upl
    -0.64
     fitting
    -0.64
     redu
    -0.63
     piping
    -0.63
     ratios
    -0.63
     rooft
    -0.62
     reckoning
    -0.62
    POSITIVE LOGITS
    ?]
    1.58
    !]
    1.46
    sic
    1.40
     edit
    1.38
    email
    1.29
    actionDate
    1.28
    REDACTED
    1.25
    ](
    1.22
    â̦]
    1.20
    ...]
    1.20
    Activations Density 0.163%

    No Known Activations