© 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. 11-RES-JB
    11. 13299
    Prev
    Next
    INDEX
    Explanations

    names of businesses or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns referring to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Defendant
    -0.82
     Defendants
    -0.81
    Statement
    -0.80
     Pastebin
    -0.75
    sic
    -0.74
    soType
    -0.72
    ÙĦ
    -0.72
     Mandatory
    -0.69
     Plaintiff
    -0.68
    BRE
    -0.68
    POSITIVE LOGITS
     remembers
    1.50
     recalls
    1.34
     says
    1.24
     admits
    1.21
     thinks
    1.19
     guesses
    1.19
     hopes
    1.14
     pauses
    1.13
     credits
    1.12
     knows
    1.12
    Activations Density 0.360%

    No Known Activations