© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 6993
    Prev
    Next
    INDEX
    Explanations

    words related to obligations, requirements, and standards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compliance and regulatory standards

    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
    ãĥ£
    -0.91
    assemb
    -0.71
    argon
    -0.69
    ENG
    -0.65
    kered
    -0.64
    sylv
    -0.63
    eng
    -0.61
    usted
    -0.60
    aping
    -0.59
    married
    -0.59
    POSITIVE LOGITS
    unal
    0.82
    naires
    0.76
     norms
    0.75
     criterion
    0.71
     athlet
    0.70
     requirements
    0.66
     criteria
    0.66
     laid
    0.66
     established
    0.65
     faithfully
    0.61
    Activations Density 0.394%

    No Known Activations