© 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. 9-RES-JB
    11. 7281
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and product descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to technical specifications or model identifiers

    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
     partName
    -0.67
     Unc
    -0.64
     Becky
    -0.62
     QR
    -0.61
     Downtown
    -0.60
     Genius
    -0.56
     Fallout
    -0.56
     Uncharted
    -0.55
     ADS
    -0.55
     Herald
    -0.55
    POSITIVE LOGITS
    gettable
    0.97
    oslav
    0.84
    İ
    0.82
    ipal
    0.82
    ifling
    0.81
    assic
    0.76
    opian
    0.75
    otin
    0.75
    upid
    0.73
    isoft
    0.73
    Activations Density 0.271%

    No Known Activations