© 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. 14201
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiation and conflict resolution

    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
    35
    +0.10
    0.5%
    159
    +0.10
    0.4%
    676
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.01
    676
    +0.10
    0.01
    738
    +0.10
    0.01
    Negative Logits
    ORGE
    -0.71
    WHERE
    -0.68
    BuyableInstoreAndOnline
    -0.68
    realDonaldTrump
    -0.66
     Falk
    -0.66
    Bloom
    -0.66
    strap
    -0.65
    Dro
    -0.64
    ¯¯
    -0.64
    PLA
    -0.64
    POSITIVE LOGITS
    oti
    1.61
    otiation
    1.58
    atives
    1.37
    ativity
    1.25
    atively
    1.15
    rito
    1.14
    lect
    1.10
    lected
    1.08
    ative
    1.00
    neg
    0.99
    Activations Density 0.012%

    No Known Activations