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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10017
    Prev
    Next
    INDEX
    Explanations

    addresses or locations mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to addresses and related address information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lime
    -0.72
    fps
    -0.70
    issance
    -0.67
    ISM
    -0.66
     fps
    -0.66
     Flavoring
    -0.64
    exper
    -0.64
    SHIP
    -0.64
    ifact
    -0.63
    arily
    -0.62
    POSITIVE LOGITS
     addr
    0.86
     redacted
    0.82
     spoof
    0.78
     Address
    0.77
    Book
    0.75
    chool
    0.72
     192
    0.69
    info
    0.68
    book
    0.68
     book
    0.68
    Activations Density 0.044%

    No Known Activations