Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 19
    Prev
    Next
    INDEX
    Explanations

    content related to political figures and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    283
    +0.13
    0.9%
    756
    +0.11
    0.7%
    459
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.13
    0.03
    756
    +0.11
    -0.16
    570
    +0.11
    -0.02
    Negative Logits
     Canaver
    -0.53
    estern
    -0.46
    odcast
    -0.38
    Picture
    -0.36
     PARK
    -0.36
    podcast
    -0.35
     Patreon
    -0.35
     Anonymous
    -0.35
     âĢº
    -0.34
     Geek
    -0.34
    POSITIVE LOGITS
    .).
    0.80
    )).
    0.77
    ?).
    0.70
    ).[
    0.70
    )."
    0.68
    ]."
    0.67
    ).
    0.67
    }.
    0.65
    ]).
    0.62
    %).
    0.61
    Activations Density 18.821%

    No Known Activations