© 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. 16814
    Prev
    Next
    INDEX
    Explanations

    words related to cleanliness or tidying up after oneself

    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
    628
    +0.12
    0.5%
    239
    +0.10
    0.5%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.12
    0.02
    628
    +0.10
    0.02
    239
    +0.10
    0.02
    Negative Logits
    SPONSORED
    -0.83
    yip
    -0.69
     monop
    -0.69
    isSpecialOrderable
    -0.69
    thood
    -0.68
    antom
    -0.65
    argument
    -0.62
    REL
    -0.62
    uo
    -0.61
    ĺħ
    -0.61
    POSITIVE LOGITS
     residue
    0.89
     polluted
    0.83
     backlog
    0.83
     toilets
    0.82
     slate
    0.81
     linen
    0.80
     stains
    0.80
     toxins
    0.78
     ponds
    0.78
     disinfect
    0.77
    Activations Density 0.160%

    No Known Activations