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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1325
    Prev
    Next
    INDEX
    Explanations

    information related to different species and their habitats

    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
    151
    +0.15
    0.7%
    223
    +0.10
    0.5%
    483
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.15
    0.10
    343
    +0.10
    0.06
    537
    +0.10
    0.07
    Negative Logits
    soDeliveryDate
    -0.90
    Gate
    -0.82
     editorial
    -0.81
    Financial
    -0.80
    Offline
    -0.77
    HUD
    -0.76
    Money
    -0.75
     billing
    -0.74
     financially
    -0.73
     budgetary
    -0.73
    POSITIVE LOGITS
     species
    1.58
     larvae
    1.55
     beetles
    1.39
     genus
    1.39
     insects
    1.37
    species
    1.34
     fungus
    1.32
     mammals
    1.32
     beetle
    1.31
     fungi
    1.31
    Activations Density 1.828%

    No Known Activations