© 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. 23040
    Prev
    Next
    INDEX
    Explanations

    words related to statements indicating an instruction or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "all" and variations of capitalization

    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
    hyde
    -0.76
     Kamp
    -0.76
    rir
    -0.70
    ãĤ©
    -0.69
     mathemat
    -0.67
    uable
    -0.64
    sein
    -0.64
    rought
    -0.63
     Gork
    -0.63
    unin
    -0.62
    POSITIVE LOGITS
    igator
    1.04
    ocations
    0.94
    iances
    0.92
    iance
    0.92
    usions
    0.90
    ergic
    0.88
    ocation
    0.88
    igators
    0.86
    owed
    0.85
     sorts
    0.84
    Activations Density 0.058%

    No Known Activations