© 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. 18803
    Prev
    Next
    INDEX
    Explanations

    terms related to contrasts between different options or perspectives

    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
    447
    +0.10
    0.5%
    737
    +0.10
    0.4%
    377
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.10
    0.03
    737
    +0.10
    0.03
    724
    +0.09
    0.04
    Negative Logits
    deen
    -0.83
    den
    -0.67
    inflamm
    -0.67
    ENTS
    -0.66
    Tickets
    -0.66
    aband
    -0.65
    uled
    -0.65
     Regist
    -0.62
    azeera
    -0.62
    ITED
    -0.61
    POSITIVE LOGITS
     between
    1.51
    between
    1.29
     Between
    1.20
     BET
    1.02
    otomy
    0.99
     separating
    0.92
    Between
    0.82
     inherent
    0.81
     dilemma
    0.81
     favoring
    0.79
    Activations Density 0.143%

    No Known Activations