© 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. 9407
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific news organization

    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
    484
    +0.13
    0.6%
    290
    +0.09
    0.4%
    4
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.01
    235
    +0.09
    0.01
    484
    +0.09
    0.01
    Negative Logits
    regn
    -0.68
     awoken
    -0.65
     rounding
    -0.62
    rolet
    -0.62
    amac
    -0.60
     tuna
    -0.59
     Williamson
    -0.59
     Timberwolves
    -0.59
     MLG
    -0.58
    rior
    -0.57
    POSITIVE LOGITS
    legraph
    1.03
    shire
    0.89
     Tycoon
    0.87
    orial
    0.83
    biz
    0.83
    soever
    0.81
     Telegraph
    0.80
    ic
    0.79
     Newsp
    0.77
    igel
    0.77
    Activations Density 0.014%

    No Known Activations