© 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. 6053
    Prev
    Next
    INDEX
    Explanations

    dates and years

    oai_token-act-pair · gpt-3.5-turbo

    dates and events related to historical or significant occurrences

    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
    cock
    -0.82
    nox
    -0.65
    ele
    -0.65
    ickle
    -0.64
    assad
    -0.62
     tremend
    -0.62
    perm
    -0.62
    Exit
    -0.62
    olerance
    -0.60
     awa
    -0.60
    POSITIVE LOGITS
    Downloadha
    0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.67
     by
    0.63
     pursuant
    0.63
    ãĤ´ãĥ³
    0.63
    BuyableInstoreAndOnline
    0.62
     alongside
    0.62
     "$:/
    0.61
     è£ıè
    0.61
    å°Ĩ
    0.61
    Activations Density 0.628%

    No Known Activations