© 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 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. 10970
    Prev
    Next
    INDEX
    Explanations

    locations or settings and physical actions happening within those locations

    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
    480
    +0.28
    1.4%
    447
    +0.20
    1.0%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.10
    575
    +0.20
    0.08
    351
    +0.12
    0.05
    Negative Logits
    eatures
    -0.61
     resid
    -0.59
    External
    -0.58
     versatility
    -0.58
    FORMATION
    -0.58
    ŃĶ
    -0.57
     unspecified
    -0.57
     complementary
    -0.56
    çĶ°
    -0.55
     newcom
    -0.55
    POSITIVE LOGITS
     anymore
    1.33
     someday
    1.02
     anytime
    0.94
     or
    0.92
     tomorrow
    0.90
     nor
    0.90
     forever
    0.78
     sooner
    0.76
    .?
    0.74
    ?",
    0.73
    Activations Density 0.844%

    No Known Activations