© 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 3072
    9. 8-RES_FS3072-JB
    11. 3010
    Prev
    Next
    INDEX
    Explanations

    percentages mentioned in a political context

    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
    756
    +0.34
    2.1%
    459
    +0.22
    1.3%
    497
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.34
    -0.03
    459
    +0.22
    0.20
    570
    +0.14
    0.01
    Negative Logits
     Canaver
    -0.62
    ¶
    -0.53
    Picture
    -0.48
     NRL
    -0.44
    ãĥ¤
    -0.41
     âĵĺ
    -0.41
     Hearthstone
    -0.41
    ©¶æ
    -0.41
     NRS
    -0.41
    estern
    -0.40
    POSITIVE LOGITS
    .).
    0.81
    )."
    0.70
    ).
    0.67
    ]."
    0.63
    ).[
    0.63
    %).
    0.63
    }.
    0.62
    .)
    0.61
    !).
    0.60
    ?).
    0.59
    Activations Density 12.285%

    No Known Activations