© 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. 23591
    Prev
    Next
    INDEX
    Explanations

    cities and geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or movement across different places

    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
     ``
    -0.77
     CODE
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
     indemn
    -0.61
    %%
    -0.60
     ''
    -0.60
    Reviewer
    -0.60
     "$:/
    -0.57
    OTH
    -0.57
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.57
    POSITIVE LOGITS
    livion
    0.74
    ulkan
    0.72
    inelli
    0.69
    ropolis
    0.68
    ritch
    0.67
    arettes
    0.67
    legate
    0.66
    rossover
    0.65
    oppable
    0.65
    skirts
    0.65
    Activations Density 0.268%

    No Known Activations