© 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. 9-RES-JB
    11. 15351
    Prev
    Next
    INDEX
    Explanations

    terms related to explanations or descriptions, particularly in technical or informational contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to science, astronomy, and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abal
    -0.61
    cade
    -0.61
    lihood
    -0.61
     epit
    -0.60
    etts
    -0.58
    inently
    -0.57
     Borders
    -0.57
    lag
    -0.56
    matter
    -0.55
    ercise
    -0.55
    POSITIVE LOGITS
    Asset
    0.77
    çİĭ
    0.76
    BuyableInstoreAndOnline
    0.74
    umbn
    0.68
     ILCS
    0.68
    Ble
    0.63
    anooga
    0.63
     MFT
    0.62
    reality
    0.62
    racuse
    0.60
    Activations Density 0.293%

    No Known Activations