© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1178
    Prev
    Next
    INDEX
    Explanations

    Advertisements or promotional content

    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
    314
    +0.12
    0.6%
    617
    +0.11
    0.5%
    430
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.12
    0.03
    314
    +0.11
    0.00
    220
    +0.10
    0.03
    Negative Logits
    aird
    -0.69
    ifice
    -0.60
    rame
    -0.60
     Oo
    -0.59
    anchester
    -0.59
    emet
    -0.58
    nce
    -0.55
    istries
    -0.54
    gha
    -0.54
     besides
    -0.53
    POSITIVE LOGITS
    çĶ°
    0.72
    ¥µ
    0.69
    HI
    0.68
    =~=~
    0.66
    ãĥĭ
    0.64
    EGIN
    0.64
     Version
    0.63
    /-
    0.62
    ventus
    0.62
    ãĥ³ãĤ¸
    0.61
    Activations Density 0.272%

    No Known Activations