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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11825
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues, particularly gender-related conflicts and political discussions

    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
    447
    +0.21
    1.2%
    373
    +0.19
    1.1%
    642
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.21
    -0.10
    281
    +0.19
    0.03
    567
    +0.09
    0.03
    Negative Logits
    .).
    -0.79
    ]).
    -0.74
    ]."
    -0.72
    )).
    -0.69
    }.
    -0.64
    .'"
    -0.62
    ).[
    -0.62
    ].
    -0.60
    )."
    -0.60
    !).
    -0.58
    POSITIVE LOGITS
    ãĥĺãĥ©
    0.56
    izont
    0.50
    ãĥİ
    0.48
    emale
    0.48
    akeru
    0.46
    reens
    0.45
    esides
    0.45
    NAME
    0.43
    renheit
    0.43
    aeda
    0.42
    Activations Density 2.279%

    No Known Activations