© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    names of places, specifically related to architecture

    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
    496
    +0.16
    0.7%
    503
    +0.10
    0.5%
    695
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.16
    0.02
    695
    +0.10
    0.02
    110
    +0.09
    0.02
    Negative Logits
    éĹĺ
    -0.86
    eers
    -0.69
    URES
    -0.67
    UCT
    -0.66
     Tone
    -0.65
     semantics
    -0.63
    xual
    -0.63
    BOOK
    -0.63
    代
    -0.63
    xon
    -0.61
    POSITIVE LOGITS
    assment
    1.14
    vard
    1.08
    riers
    1.07
    rod
    1.06
    rier
    1.03
    rim
    1.01
    rah
    0.99
    assed
    0.96
    rowing
    0.95
    poon
    0.93
    Activations Density 0.009%

    No Known Activations