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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1499
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical features or details

    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
    481
    +0.18
    0.9%
    164
    +0.11
    0.5%
    369
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.18
    0.08
    43
    +0.11
    0.06
    433
    +0.09
    0.06
    Negative Logits
    iku
    -0.67
    opal
    -0.66
    raft
    -0.65
    erity
    -0.65
    OLOG
    -0.65
    ":"/
    -0.63
    gression
    -0.63
    aga
    -0.62
    lust
    -0.62
    ¬¼
    -0.62
    POSITIVE LOGITS
     etc
    1.60
    etc
    1.12
     and
    0.83
     respectively
    0.80
     ect
    0.79
     assorted
    0.74
     plus
    0.74
     et
    0.65
     };
    0.59
     AND
    0.58
    Activations Density 0.304%

    No Known Activations