© 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. 17267
    Prev
    Next
    INDEX
    Explanations

    names of photographers and photo credits

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their affiliations or associations with images

    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
    ccording
    -0.87
     arrang
    -0.74
     eleph
    -0.73
     streng
    -0.71
     resil
    -0.70
    comings
    -0.69
     awa
    -0.67
    conservancy
    -0.66
    ãĥīãĥ©
    -0.65
    aditional
    -0.65
    POSITIVE LOGITS
     *)
    0.66
    icio
    0.66
     Vaughn
    0.66
    JV
    0.65
     Levine
    0.64
     Pau
    0.64
    miah
    0.63
     Nielsen
    0.62
     Owen
    0.62
     Pix
    0.62
    Activations Density 0.089%

    No Known Activations