© 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. 18705
    Prev
    Next
    INDEX
    Explanations

    names of individuals or publications

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    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
    ãĢİ
    -0.55
     Reincarn
    -0.55
    ,[
    -0.53
     Examination
    -0.50
     (?,
    -0.49
    thood
    -0.48
     Refuge
    -0.47
    ãĢIJ
    -0.47
    cerning
    -0.47
    ãĥīãĥ©ãĤ´ãĥ³
    -0.46
    POSITIVE LOGITS
    ulton
    0.82
    utterstock
    0.81
    photos
    0.80
    /)
    0.74
    )/
    0.73
     Photography
    0.72
     /
    0.69
    reenshot
    0.69
    ./
    0.67
     Shutterstock
    0.66
    Activations Density 0.107%

    No Known Activations