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. 4507
    Prev
    Next
    INDEX
    Explanations

    explicit names, possibly of people

    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
    373
    +0.36
    2.4%
    447
    +0.23
    1.5%
    157
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.36
    -0.14
    680
    +0.23
    0.04
    157
    +0.06
    0.09
    Negative Logits
    .</
    -0.74
    .).
    -0.73
    ]."
    -0.68
    }.
    -0.65
    $.
    -0.64
    )).
    -0.64
    %.
    -0.64
    )."
    -0.63
    ".
    -0.63
    .''
    -0.62
    POSITIVE LOGITS
     Canaver
    0.42
    estern
    0.38
     Lauder
    0.38
     Malf
    0.37
    reenshots
    0.36
     Expand
    0.36
     partName
    0.35
    ':
    0.35
     Bris
    0.34
    anchester
    0.34
    Activations Density 5.675%

    No Known Activations