© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9860
    Prev
    Next
    INDEX
    Explanations

    statements expressing opinions or providing advice related to a particular topic

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.50
    2.6%
    266
    +0.12
    0.6%
    7
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.50
    0.01
    266
    +0.12
    0.11
    641
    +0.08
    0.08
    Negative Logits
    >>>>>>>>
    -0.63
    audi
    -0.61
    outhern
    -0.59
    enko
    -0.58
    cussion
    -0.58
    named
    -0.58
    olid
    -0.57
    warn
    -0.56
     Thumbnails
    -0.56
     Canaver
    -0.56
    POSITIVE LOGITS
     oneself
    0.85
     society
    0.84
     oppression
    0.81
     others
    0.81
     injust
    0.78
     oppress
    0.77
     stimuli
    0.76
     societal
    0.73
     predetermined
    0.73
     worldview
    0.72
    Activations Density 1.517%

    No Known Activations