© 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. 10-RES-JB
    11. 2986
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a request or suggestion

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},"
    -0.71
    ¶
    -0.69
    prototype
    -0.66
    AMP
    -0.61
    DN
    -0.61
    anguages
    -0.59
     Mehran
    -0.57
     constitu
    -0.57
    ](
    -0.56
    iege
    -0.56
    POSITIVE LOGITS
     yourselves
    1.43
     yourself
    1.09
     me
    0.88
     kidding
    0.86
    ichever
    0.82
     ye
    0.82
     beware
    0.80
    ifully
    0.80
     thy
    0.79
    quote
    0.78
    Activations Density 0.155%

    No Known Activations