Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 81
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.14
    0.7%
    641
    +0.11
    0.5%
    383
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.03
    635
    +0.11
    0.02
    421
    +0.10
    0.02
    Negative Logits
    cling
    -0.82
    ŃĶ
    -0.72
    hower
    -0.69
     spect
    -0.68
    rums
    -0.66
    croft
    -0.65
     general
    -0.64
    baugh
    -0.63
    ãĤ®
    -0.63
     owl
    -0.63
    POSITIVE LOGITS
    vernment
    1.27
    errilla
    1.18
    cci
    1.17
    essing
    1.15
    bernatorial
    1.14
    inea
    1.10
    arant
    1.07
    itars
    1.07
    ilt
    1.04
    arding
    1.00
    Activations Density 0.049%

    No Known Activations