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

    Neuronpedia

    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. 10003
    Prev
    Next
    INDEX
    Explanations

    Dialogue and information about political events and controversies

    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
    100
    +0.12
    0.5%
    202
    +0.10
    0.5%
    720
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.08
    720
    +0.10
    0.09
    546
    +0.10
    0.08
    Negative Logits
    ran
    -0.66
    rir
    -0.64
    cial
    -0.60
    ubb
    -0.58
    rero
    -0.57
    urry
    -0.56
    ©¶æ
    -0.55
     misunder
    -0.55
     neighbourhood
    -0.55
    raft
    -0.55
    POSITIVE LOGITS
     whereas
    1.26
     albeit
    1.14
     implying
    1.13
    rather
    1.11
    but
    1.06
     namely
    1.05
     irrespective
    1.04
     although
    1.03
     ie
    1.02
    despite
    1.02
    Activations Density 0.445%

    No Known Activations