© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    direct appeals to the reader using the word "you."

    oai_token-act-pair · gpt-3.5-turbo

    references to the reader and solicit their engagement or participation

    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
     Canaver
    -0.74
     Cao
    -0.68
    apo
    -0.68
    apes
    -0.67
    otom
    -0.67
    atown
    -0.67
    ukemia
    -0.66
    ACP
    -0.66
    ylum
    -0.66
    ioned
    -0.65
    POSITIVE LOGITS
     guys
    1.08
    tub
    1.04
    're
    0.88
    RS
    0.87
     yourselves
    0.84
     feedback
    0.82
    sylv
    0.77
     mileage
    0.74
    STON
    0.73
    TOR
    0.73
    Activations Density 0.189%

    No Known Activations