© 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. 9-RES-JB
    11. 10254
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gold" followed by a single character such as a number or a letter

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the term "Gold 2"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ATIONS
    -0.99
    ROR
    -0.68
     reperto
    -0.66
    ================================================================
    -0.65
    ========
    -0.63
     abdom
    -0.63
    ufact
    -0.62
    ABLE
    -0.61
    aneously
    -0.59
     informational
    -0.59
    POSITIVE LOGITS
    vertisement
    1.19
    smith
    1.15
    finger
    1.07
    rush
    1.07
    mund
    1.06
    stein
    1.03
    sch
    1.02
    wyn
    0.98
    fields
    0.95
    stone
    0.94
    Activations Density 0.030%

    No Known Activations