© 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. 13145
    Prev
    Next
    INDEX
    Explanations

    statements or clues in a written text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the phrase "It is" in various contexts

    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
    bies
    -0.68
    luaj
    -0.67
     IMAGES
    -0.66
    ertodd
    -0.65
     bunch
    -0.64
    esm
    -0.64
     Finish
    -0.63
     Bung
    -0.62
    igraph
    -0.61
    uffs
    -0.61
    POSITIVE LOGITS
     unclear
    1.12
     imperative
    1.07
     doubtful
    1.06
     impossible
    1.05
     unlikely
    1.01
     advisable
    1.00
     undeniable
    0.96
     conceivable
    0.96
     indeed
    0.95
     abundantly
    0.93
    Activations Density 0.121%

    No Known Activations