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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19693
    Prev
    Next
    INDEX
    Explanations

    mentions of the Electronic Frontier Foundation (EFF) or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the Electronic Frontier Foundation (EFF) and the DMCA (Digital Millennium Copyright Act)

    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
    mate
    -0.78
    mates
    -0.74
    hani
    -0.73
     Ramsay
    -0.72
     Sul
    -0.72
    castle
    -0.70
     Bulldogs
    -0.69
     Bolton
    -0.69
    alled
    -0.68
    guards
    -0.67
    POSITIVE LOGITS
    yright
    1.02
    Torrent
    1.02
     EFF
    0.87
    EFF
    0.84
    iversary
    0.84
     GOODMAN
    0.83
     DMCA
    0.83
    ODUCT
    0.79
     takedown
    0.79
    ividual
    0.76
    Activations Density 0.033%

    No Known Activations