© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18876
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to computer programming and development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.12
    0.5%
    404
    +0.11
    0.5%
    631
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.12
    0.03
    631
    +0.11
    0.02
    373
    +0.10
    -0.01
    Negative Logits
    bourg
    -0.73
     ponds
    -0.70
    ById
    -0.69
    å·
    -0.66
     pond
    -0.63
    }}}
    -0.61
    ÄŁ
    -0.60
     Oswald
    -0.59
    Bir
    -0.59
     Canaver
    -0.59
    POSITIVE LOGITS
    imity
    1.13
    etary
    0.90
    incial
    0.90
    agonist
    0.86
    hetic
    0.84
    enium
    0.81
    ession
    0.80
    bably
    0.78
    secut
    0.78
    essor
    0.78
    Activations Density 0.067%

    No Known Activations