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. 1855
    Prev
    Next
    INDEX
    Explanations

    mentions of political ideologies or extreme beliefs

    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
    109
    +0.13
    0.6%
    647
    +0.11
    0.5%
    195
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.11
    109
    +0.11
    0.06
    284
    +0.11
    0.06
    Negative Logits
    osuke
    -0.84
    ilage
    -0.81
    icative
    -0.81
    tons
    -0.80
    icating
    -0.77
    oted
    -0.76
    rooms
    -0.76
    lins
    -0.74
    shaw
    -0.73
    icate
    -0.73
    POSITIVE LOGITS
     temperatures
    0.79
     sensitivity
    0.79
     vetting
    0.76
     poverty
    0.75
     rare
    0.75
    ctic
    0.72
    reality
    0.71
     Measures
    0.69
    raviolet
    0.69
     lifestyles
    0.68
    Activations Density 1.277%

    No Known Activations