© 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. 23943
    Prev
    Next
    INDEX
    Explanations

    scientific findings and research results

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements regarding scientific findings or observations

    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
    VICE
    -0.68
     Bravo
    -0.65
    ggles
    -0.62
    ohan
    -0.59
    ospel
    -0.59
    raphics
    -0.56
     Pt
    -0.54
    ateurs
    -0.54
     Guid
    -0.53
     Netflix
    -0.52
    POSITIVE LOGITS
     anecd
    0.95
     to
    0.82
     by
    0.81
     as
    0.73
    iosis
    0.72
     clinically
    0.71
    efficient
    0.67
     preval
    0.66
     inaccur
    0.66
    ingly
    0.64
    Activations Density 0.181%

    No Known Activations