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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5524
    Prev
    Next
    INDEX
    Explanations

    phrases related to confrontation or conflict and specific numbers or terms related to a military setting

    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
    711
    +0.11
    0.5%
    641
    +0.10
    0.4%
    195
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.11
    0.07
    195
    +0.10
    0.02
    288
    +0.09
    0.08
    Negative Logits
     heterogeneity
    -0.61
    illard
    -0.58
    æĸ¹
    -0.56
     narrowed
    -0.55
    byn
    -0.55
     McInt
    -0.55
     Cheong
    -0.54
     unst
    -0.53
     culmination
    -0.53
     meantime
    -0.53
    POSITIVE LOGITS
    print
    0.80
    ibly
    0.77
    eting
    0.76
    urized
    0.76
    eval
    0.74
    ynthesis
    0.72
    ably
    0.72
    urable
    0.70
    lime
    0.67
    bol
    0.66
    Activations Density 0.692%

    No Known Activations