© 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 EvalsExportsAPI 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. 0-RES-JB
    11. 13092
    Prev
    Next
    INDEX
    Explanations

    words related to identification documents or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to identification and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spur
    -0.72
    pire
    -0.71
    aft
    -0.69
     presided
    -0.66
    hops
    -0.64
    fty
    -0.62
    verse
    -0.62
    phalt
    -0.62
     raining
    -0.61
    mega
    -0.61
    POSITIVE LOGITS
     identification
    3.83
     Identification
    3.04
     ID
    1.84
     IDs
    1.79
     ident
    1.69
     identity
    1.66
     identifying
    1.65
     identifier
    1.55
     identify
    1.49
     identifiers
    1.49
    Activations Density 0.011%

    No Known Activations