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. 4519
    Prev
    Next
    INDEX
    Explanations

    words related to nocturnal animals with emphasis on the letter sequence "ct" in them

    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
    223
    +0.12
    0.6%
    651
    +0.12
    0.5%
    355
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    651
    +0.12
    0.06
    232
    +0.12
    0.05
    Negative Logits
     Lennon
    -0.68
     Angola
    -0.66
     Wilde
    -0.65
     Leopard
    -0.64
     Mandela
    -0.62
     Leone
    -0.61
     traveller
    -0.60
    PUT
    -0.60
    FORE
    -0.59
    CE
    -0.57
    POSITIVE LOGITS
    ures
    1.54
    ured
    1.41
    urous
    1.36
    uring
    1.34
    acular
    1.33
    urers
    1.30
    orial
    1.28
    ract
    1.27
    ure
    1.17
    urer
    1.16
    Activations Density 0.466%

    No Known Activations