© 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. 6056
    Prev
    Next
    INDEX
    Explanations

    questions or desires to know about a variety of topics

    oai_token-act-pair · gpt-3.5-turbo

    questions or expressions of curiosity

    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
    onding
    -0.71
    pite
    -0.70
    ovie
    -0.66
    interstitial
    -0.66
    ©¶æ¥µ
    -0.63
     projection
    -0.62
    ufact
    -0.62
    twitch
    -0.61
     permitting
    -0.61
    edition
    -0.61
    POSITIVE LOGITS
     WHY
    1.19
     why
    1.14
     how
    1.03
     whether
    1.00
    why
    0.97
     ABOUT
    0.94
     WHERE
    0.93
     answers
    0.90
     HOW
    0.90
     about
    0.89
    Activations Density 0.098%

    No Known Activations