© 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. 4030
    Prev
    Next
    INDEX
    Explanations

    locations and specific details within news articles

    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
    481
    +0.16
    0.7%
    585
    +0.11
    0.5%
    115
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.16
    0.05
    145
    +0.11
    0.04
    65
    +0.10
    0.04
    Negative Logits
    uria
    -0.89
    ocrates
    -0.80
    matched
    -0.72
    earcher
    -0.68
    riel
    -0.66
    itars
    -0.65
    pelled
    -0.65
    idious
    -0.65
    -+-+
    -0.64
    handed
    -0.63
    POSITIVE LOGITS
     Mountains
    1.22
     Islands
    1.12
     Valley
    1.08
     River
    1.08
     Estate
    1.06
     Hotel
    1.06
     County
    1.05
     Basin
    1.04
     Peninsula
    1.04
     Hills
    1.04
    Activations Density 0.157%

    No Known Activations