© 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. 16674
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential outcomes or consequences

    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
    712
    +0.10
    0.4%
    458
    +0.09
    0.4%
    47
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.10
    0.04
    53
    +0.09
    0.04
    431
    +0.09
    0.03
    Negative Logits
    quartered
    -0.71
    fort
    -0.70
     Examination
    -0.64
    cius
    -0.63
    lex
    -0.61
    gra
    -0.60
    SHIP
    -0.60
    Maker
    -0.59
    lication
    -0.58
     aware
    -0.58
    POSITIVE LOGITS
     transpired
    1.26
     happen
    1.26
     happened
    1.21
     happ
    1.21
     happens
    1.09
     happening
    1.07
     Happ
    0.97
    ilk
    0.82
     unfolded
    0.78
     constitutes
    0.77
    Activations Density 0.104%

    No Known Activations