© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17258
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks, indicating dialogue or quoted speech

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ominated
    -0.73
     peg
    -0.71
     reception
    -0.67
    imity
    -0.65
    isl
    -0.64
    opter
    -0.63
    xtap
    -0.63
    tein
    -0.61
    inence
    -0.61
     Swordsman
    -0.60
    POSITIVE LOGITS
    Mother
    0.72
    Rust
    0.69
    --------------------------------------------------------
    0.65
    Rah
    0.63
     Mandela
    0.62
    TPS
    0.61
    ¢
    0.61
    wikipedia
    0.60
    SIGN
    0.59
    cause
    0.59
    Activations Density 0.146%

    No Known Activations