© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8622
    Prev
    Next
    INDEX
    Explanations

    phrases with formatting inconsistency, possibly indicating a specific type of error

    oai_token-act-pair · gpt-3.5-turbo

    numeric sequences or dates

    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
     Mub
    -0.67
     plagiar
    -0.64
     Benz
    -0.62
     Hast
    -0.61
     REM
    -0.60
     Bale
    -0.60
     Bots
    -0.59
     Buckingham
    -0.59
     Photograph
    -0.59
     Bout
    -0.58
    POSITIVE LOGITS
    inventoryQuantity
    0.82
    amar
    0.70
    culus
    0.67
    James
    0.67
    roma
    0.66
    Kyle
    0.63
    usable
    0.62
    Ian
    0.62
    Hillary
    0.62
    Rating
    0.61
    Activations Density 0.093%

    No Known Activations