© 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. 17949
    Prev
    Next
    INDEX
    Explanations

    zip codes

    oai_token-act-pair · gpt-3.5-turbo

    references to zip codes

    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
    raising
    -0.79
    nesota
    -0.79
    emies
    -0.78
    igmatic
    -0.76
    nen
    -0.74
    ¯¯
    -0.73
     Democr
    -0.72
    rums
    -0.72
    nces
    -0.72
    ership
    -0.71
    POSITIVE LOGITS
    Zip
    0.87
     zip
    0.84
     Zip
    0.78
    ijn
    0.72
     sum
    0.72
    zip
    0.72
    pees
    0.72
    !/
    0.71
    INO
    0.71
    edia
    0.69
    Activations Density 0.028%

    No Known Activations