© 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. 4553
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and criminal cases involving deadly incidents

    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
    651
    +0.12
    0.5%
    726
    +0.11
    0.5%
    600
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.12
    0.02
    700
    +0.11
    0.02
    651
    +0.11
    0.02
    Negative Logits
    EStream
    -0.68
     sheer
    -0.67
    SPONSORED
    -0.67
    Ļ½
    -0.66
    ¥ŀ
    -0.66
    NetMessage
    -0.65
    KER
    -0.64
    «ĺ
    -0.64
     destro
    -0.62
     precedent
    -0.60
    POSITIVE LOGITS
    amins
    1.12
    chell
    1.07
    uary
    1.03
    ocracy
    1.00
    anium
    0.97
    rogen
    0.92
    onal
    0.90
    ivities
    0.89
    ople
    0.88
    chers
    0.88
    Activations Density 0.035%

    No Known Activations