© 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. 7-RES-JB
    11. 2107
    Prev
    Next
    INDEX
    Explanations

    references to reading additional content or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to additional information or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clave
    -0.61
     Kodi
    -0.59
     GMO
    -0.57
     Miliband
    -0.55
     Mountain
    -0.55
     Patel
    -0.55
     Norman
    -0.55
     Alpine
    -0.55
     Florence
    -0.55
     Marshall
    -0.54
    POSITIVE LOGITS
    etheless
    0.93
    anwhile
    0.92
    interrupted
    0.92
    [/
    0.82
    jri
    0.72
     dunno
    0.70
    onis
    0.69
    imately
    0.68
    ................
    0.67
    Contract
    0.67
    Activations Density 0.167%

    No Known Activations