© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 14894
    Prev
    Next
    INDEX
    Explanations

    Sentences starting with "According to."

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative sources or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confidence
    -0.74
     welcome
    -0.69
     patience
    -0.65
     success
    -0.64
    bench
    -0.64
     win
    -0.64
     steam
    -0.63
     pleasure
    -0.63
     peace
    -0.63
     wild
    -0.63
    POSITIVE LOGITS
     According
    3.03
    According
    2.33
    ccording
    2.22
    according
    1.96
     Apparently
    1.71
     according
    1.68
     Among
    1.53
     Says
    1.48
     Specifically
    1.47
     Interestingly
    1.46
    Activations Density 0.013%

    No Known Activations