© 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. 11-RES-JB
    11. 18760
    Prev
    Next
    INDEX
    Explanations

    phrases expressing knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating familiarity or prior knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oreal
    -0.73
    xa
    -0.71
    rontal
    -0.71
    vati
    -0.68
    oyer
    -0.67
    orthy
    -0.66
    ongevity
    -0.65
    cific
    -0.64
    iterranean
    -0.63
    foreseen
    -0.63
    POSITIVE LOGITS
     already
    0.73
     by
    0.68
     yourselves
    0.68
     me
    0.67
     BY
    0.66
    76561
    0.60
    tale
    0.60
     guessed
    0.58
     about
    0.56
     that
    0.56
    Activations Density 0.128%

    No Known Activations