© 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. 6-RES-JB
    11. 9400
    Prev
    Next
    INDEX
    Explanations

    contractions where a word is abbreviated with an apostrophe and the following word begins with a lowercase letter

    oai_token-act-pair · gpt-3.5-turbo

    negative imperative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erial
    -0.72
    creen
    -0.69
    ELD
    -0.65
    potion
    -0.65
    currency
    -0.63
    parser
    -0.63
     booted
    -0.62
    pot
    -0.62
    virt
    -0.62
    chrom
    -0.61
    POSITIVE LOGITS
     yourselves
    0.96
     Yourself
    0.91
     yourself
    0.89
     hesitate
    0.88
    omsday
    0.81
     underestimate
    0.81
     forget
    0.80
     thou
    0.75
     listen
    0.75
     bother
    0.74
    Activations Density 0.061%

    No Known Activations