© 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. 23335
    Prev
    Next
    INDEX
    Explanations

    names consisting of two words with a hyphen in between them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jean," particularly in a professional or influential context

    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
    tsky
    -0.79
    ODUCT
    -0.69
    dest
    -0.69
    ecause
    -0.69
    OWS
    -0.68
    ilers
    -0.68
    irlf
    -0.67
    aneers
    -0.66
     Uzbek
    -0.65
    ãĥ¼ãĥ³
    -0.65
    POSITIVE LOGITS
    ette
    1.10
     Claude
    1.04
    Marie
    1.00
    etta
    0.99
    Cla
    0.98
     Jacques
    0.98
     Francois
    0.95
     Marie
    0.95
     Laf
    0.93
    enne
    0.91
    Activations Density 0.034%

    No Known Activations