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 6144
    5. 8-RES_FS6144-JB
    6. 5375
    Prev
    Next
    INDEX
    Explanations

    references to personal loss and adversity

    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%
    245
    +0.11
    0.5%
    533
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.05
    362
    +0.11
    0.05
    137
    +0.10
    0.03
    Negative Logits
    Statement
    -0.73
    LLOW
    -0.72
     solicitation
    -0.71
    ç«
    -0.70
    DIT
    -0.70
    Iss
    -0.66
    DEBUG
    -0.65
    Minimum
    -0.65
    taboola
    -0.64
    SPONSORED
    -0.64
    POSITIVE LOGITS
     virginity
    1.30
     sanity
    1.07
     innocence
    1.05
     credibility
    1.04
     dignity
    1.00
     immortality
    0.97
     freedoms
    0.93
     momentum
    0.93
     footing
    0.91
     composure
    0.91
    Activations Density 0.469%

    No Known Activations