© 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. 8-RES-JB
    11. 14136
    Prev
    Next
    INDEX
    Explanations

    phrases related to similarity or continuity

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or analogies using the word "same."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    cht
    -0.63
    henko
    -0.60
    Fine
    -0.58
    bit
    -0.57
    hess
    -0.56
    optional
    -0.56
     ._
    -0.56
    cli
    -0.56
    conference
    -0.56
    -)
    -0.55
    POSITIVE LOGITS
     predecessors
    0.86
    senal
    0.78
    osponsors
    0.78
     redes
    0.74
    én
    0.73
    irlf
    0.73
    ayn
    0.68
     exting
    0.68
    isd
    0.68
     counterparts
    0.67
    Activations Density 0.224%

    No Known Activations