© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 11465
    Prev
    Next
    INDEX
    Explanations

    mentions of names related to a specific person or topic, in this case the name "Elliott Rodger"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Elliot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    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

    Negative Logits
    hip
    -0.90
    arily
    -0.78
    atile
    -0.72
    rowing
    -0.72
    ppelin
    -0.72
    ifiable
    -0.71
    raviolet
    -0.70
    atorium
    -0.69
    alities
    -0.69
    itate
    -0.69
    POSITIVE LOGITS
    âķIJâķIJ
    0.76
    backer
    0.75
     Cyrus
    0.69
     Dickinson
    0.69
    lli
    0.66
    Draft
    0.62
    lynn
    0.62
    Tra
    0.62
    TE
    0.62
    phony
    0.61
    Activations Density 0.073%

    No Known Activations