© 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 EvalsExportsAPI 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. 8940
    Prev
    Next
    INDEX
    Explanations

    names of geographical regions

    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
    635
    +0.13
    0.6%
    336
    +0.10
    0.5%
    383
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.02
    635
    +0.10
    0.02
    421
    +0.10
    0.02
    Negative Logits
    cling
    -0.77
    ŃĶ
    -0.68
     spect
    -0.67
    baugh
    -0.67
    ãĤ®
    -0.65
    rums
    -0.65
     general
    -0.63
    lihood
    -0.63
     owl
    -0.62
     womb
    -0.62
    POSITIVE LOGITS
    vernment
    1.20
    essing
    1.15
    itars
    1.14
    errilla
    1.12
    cci
    1.08
    bernatorial
    1.06
    pton
    1.02
    arant
    1.00
    ilt
    1.00
    zzle
    0.94
    Activations Density 0.008%

    No Known Activations