© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22109
    Prev
    Next
    INDEX
    Explanations

    mentions of specific topics or headings within texts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "About" indicating a reference to time or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãģ®ç
    -0.79
    ignt
    -0.71
    among
    -0.68
    Ùĩ
    -0.65
     slightest
    -0.64
    intend
    -0.64
     funn
    -0.62
     accum
    -0.61
    imposed
    -0.61
    ,,,,
    -0.59
    POSITIVE LOGITS
     Us
    1.34
     Languages
    0.86
     Yourself
    0.84
     Me
    0.83
     Shots
    0.78
     Author
    0.76
     This
    0.72
     Fires
    0.72
     Paste
    0.71
     Them
    0.70
    Activations Density 0.019%

    No Known Activations