© 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. 10-RES-JB
    11. 12871
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and business dealings

    oai_token-act-pair · gpt-3.5-turbo

    statements about significant events or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.61
     tutor
    -0.56
     jargon
    -0.55
     acronym
    -0.55
     slang
    -0.54
     salesman
    -0.53
     pund
    -0.52
     advert
    -0.51
     referee
    -0.51
     suburb
    -0.50
    POSITIVE LOGITS
    DragonMagazine
    0.68
    respective
    0.67
    omever
    0.66
    oubtedly
    0.64
    whatever
    0.63
     sooner
    0.63
    Interested
    0.63
     indeed
    0.62
    ĵĺ
    0.61
    .","
    0.60
    Activations Density 1.137%

    No Known Activations