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

    Neuronpedia

    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. 20454
    Prev
    Next
    INDEX
    Explanations

    news article sections

    oai_token-act-pair · gpt-3.5-turbo

    references to articles or legal documentation

    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
    cffffcc
    -0.79
    adows
    -0.78
    isky
    -0.70
     Lanka
    -0.69
    rals
    -0.68
    nesota
    -0.67
    etsk
    -0.67
    cffff
    -0.66
    jri
    -0.65
    asters
    -0.64
    POSITIVE LOGITS
     Continued
    0.97
    ICLE
    0.85
    meal
    0.83
    witz
    0.75
     XVI
    0.72
     VIII
    0.69
     Tags
    0.68
     VII
    0.66
    ual
    0.66
     XX
    0.65
    Activations Density 0.022%

    No Known Activations