© 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. 17261
    Prev
    Next
    INDEX
    Explanations

    locations and addresses

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and associated numerical data such as addresses

    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
     WATCHED
    -0.88
    ADVERTISEMENT
    -0.71
    Pin
    -0.64
    ories
    -0.64
     portfolios
    -0.62
     digs
    -0.62
    vous
    -0.60
    ['
    -0.60
     batted
    -0.58
     ultras
    -0.58
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    0.88
    Tel
    0.75
    tel
    0.69
    soType
    0.67
     Telephone
    0.66
    FINE
    0.66
    Phone
    0.65
     701
    0.62
     Phone
    0.61
    fax
    0.60
    Activations Density 0.143%

    No Known Activations