© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19368
    Prev
    Next
    INDEX
    Explanations

    terms related to access, such as "open-access," "electronic access," "wheelchair accessible," and "early access."

    oai_token-act-pair · gpt-3.5-turbo

    references to access in various contexts

    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
    stal
    -0.81
    abouts
    -0.80
    geist
    -0.76
    balls
    -0.74
    =-=-=-=-
    -0.73
    swick
    -0.70
    thal
    -0.69
    UF
    -0.68
    =-=-=-=-=-=-=-=-
    -0.68
    cular
    -0.65
    POSITIVE LOGITS
     Format
    0.71
     Literary
    0.68
    çīĪ
    0.68
     Membership
    0.68
     Access
    0.66
     Digital
    0.66
     Lak
    0.65
    aucus
    0.64
     Attribution
    0.64
     Rights
    0.62
    Activations Density 0.038%

    No Known Activations