© 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. 6208
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or information from the audience

    oai_token-act-pair · gpt-3.5-turbo

    phrases that request information or feedback

    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
    adic
    -0.67
    tan
    -0.65
     Demons
    -0.62
    kered
    -0.61
    ©¶æ
    -0.61
    mur
    -0.60
    aryl
    -0.59
    ĪĴ
    -0.59
    Catalog
    -0.58
     Zamb
    -0.58
    POSITIVE LOGITS
     beforehand
    0.90
     ASAP
    0.86
     how
    0.84
    ledge
    0.80
    ledged
    0.76
     via
    0.76
     promptly
    0.76
     whats
    0.73
     hello
    0.73
     WARN
    0.73
    Activations Density 0.047%

    No Known Activations