© 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. 4918
    Prev
    Next
    INDEX
    Explanations

    instances of geographical locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the number "six" in various contexts

    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
    igation
    -0.70
     includ
    -0.70
    Offline
    -0.69
    BIP
    -0.68
    inating
    -0.68
    webkit
    -0.68
    ained
    -0.66
    ifice
    -0.66
    OCK
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
    POSITIVE LOGITS
    teen
    1.39
    een
    1.19
     Hundred
    1.11
    fold
    1.06
     Thousand
    1.04
    teenth
    0.95
     hundred
    0.95
     Isles
    0.92
    eenth
    0.90
     Kingdoms
    0.90
    Activations Density 0.061%

    No Known Activations