© 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. 10-RES-JB
    11. 21555
    Prev
    Next
    INDEX
    Explanations

    informative statements starting with "from the" or "the"

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or references to a source, particularly focusing on context and attribution

    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
     eventually
    -0.79
     having
    -0.77
     repr
    -0.76
     every
    -0.73
     whatever
    -0.73
     tending
    -0.72
     cues
    -0.72
     initially
    -0.72
     deciding
    -0.71
     requiring
    -0.71
    POSITIVE LOGITS
    odore
    1.31
     Editors
    1.07
    Score
    1.07
     Authors
    1.07
     Author
    1.05
     author
    1.04
    atre
    1.01
    resa
    0.95
    Anti
    0.93
     Editor
    0.90
    Activations Density 0.155%

    No Known Activations