© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    quotations from various people

    oai_token-act-pair · gpt-3.5-turbo

    punctuations indicating quotes or significant statements

    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
     Herald
    -0.59
    scribe
    -0.56
    vert
    -0.55
     Marshal
    -0.55
    士
    -0.54
    DAQ
    -0.54
    \\\\\\\\
    -0.53
    ORPG
    -0.53
    rones
    -0.52
    heid
    -0.52
    POSITIVE LOGITS
     "'
    1.19
     "[
    1.17
     "...
    1.14
     "âĢ¦
    1.11
     "(
    1.03
     "_
    1.02
     "
    1.01
     ''
    1.01
     ``
    1.00
     '[
    0.98
    Activations Density 0.116%

    No Known Activations