© 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. 10271
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical values or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical totals or numeric data

    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
     trave
    -0.60
    pring
    -0.60
     Presence
    -0.58
     condem
    -0.58
     disadvant
    -0.58
     adhere
    -0.58
     incre
    -0.54
     reiterate
    -0.53
     presence
    -0.53
     summarize
    -0.53
    POSITIVE LOGITS
     eight
    1.16
     thirteen
    1.13
     seven
    1.11
     six
    1.10
     nine
    1.10
     fourteen
    1.08
     sixteen
    1.07
     eleven
    1.04
     seventeen
    1.03
     nineteen
    1.02
    Activations Density 0.074%

    No Known Activations