© 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 24576
    9. 8-RES_FS24576-JB
    11. 19880
    Prev
    Next
    INDEX
    Explanations

    references to entities or topics related to the acronym "Q."

    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
    383
    +0.10
    0.4%
    635
    +0.09
    0.4%
    709
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    733
    +0.10
    0.02
    213
    +0.09
    0.02
    286
    +0.09
    0.02
    Negative Logits
    wagen
    -0.84
    fulness
    -0.72
    ufact
    -0.70
     Lauder
    -0.68
     Nadu
    -0.64
     Awakens
    -0.64
    baugh
    -0.62
     readable
    -0.62
    fitting
    -0.61
     hers
    -0.61
    POSITIVE LOGITS
    UE
    1.20
    ues
    1.16
    ued
    1.11
    ubes
    1.06
    addafi
    1.06
    WER
    1.04
    atari
    0.97
    atar
    0.96
    LD
    0.93
    iu
    0.91
    Activations Density 0.028%

    No Known Activations