© 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. 8-RES-JB
    11. 18439
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization

    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
     encour
    -0.71
     Granger
    -0.68
    creen
    -0.66
     Sorceress
    -0.62
     Xperia
    -0.61
     Garc
    -0.61
     cov
    -0.61
     colourful
    -0.60
     slack
    -0.60
     Santos
    -0.59
    POSITIVE LOGITS
    senal
    1.45
    ansom
    1.22
    abbit
    1.13
    haps
    1.08
    agnar
    1.07
    acing
    1.07
    itchie
    1.06
    OUP
    1.05
    ICH
    1.02
    utherford
    1.02
    Activations Density 0.042%

    No Known Activations