© 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. 19353
    Prev
    Next
    INDEX
    Explanations

    technical specifications or features of a product

    oai_token-act-pair · gpt-3.5-turbo

    references to advanced technology and its specifications

    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
    senal
    -0.65
    ensibly
    -0.65
     quint
    -0.64
    abouts
    -0.63
    eworks
    -0.63
    ername
    -0.61
    rils
    -0.60
    adem
    -0.60
    odox
    -0.59
    atis
    -0.59
    POSITIVE LOGITS
     Norn
    0.74
    ↵
    0.74
    âĵĺ
    0.65
     Instructions
    0.63
    "},{"
    0.63
    Includes
    0.62
    <|endoftext|>
    0.61
    ETF
    0.61
    */
    0.61
    "}],"
    0.59
    Activations Density 0.148%

    No Known Activations