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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7015
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming codes involving numbers and variables

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and data related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.87
    -$
    -0.70
    âĢij
    -0.67
    -[
    -0.64
    -'
    -0.64
    âĢIJ
    -0.62
    -.
    -0.61
    -+
    -0.58
    -)
    -0.58
    uyomi
    -0.57
    POSITIVE LOGITS
    dfx
    0.56
    rued
    0.54
    uba
    0.53
    uate
    0.51
    ede
    0.51
     externalToEVAOnly
    0.50
    edes
    0.49
    years
    0.49
    poons
    0.49
    urations
    0.47
    Activations Density 0.605%

    No Known Activations