© 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. 12-RES-JB
    11. 4888
    Prev
    Next
    INDEX
    Explanations

    names and initials, specifically with emphasis on the letter 'V' followed by a number

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to specific individuals or entities identified by a 'V' prefix

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ourselves
    -0.76
     multiplied
    -0.70
     namely
    -0.68
     something
    -0.67
     excluding
    -0.67
     AAA
    -0.67
     assuming
    -0.67
     PLA
    -0.66
     combined
    -0.65
     coupled
    -0.64
    POSITIVE LOGITS
    ickers
    1.29
    idal
    1.25
    aughters
    1.20
    ettel
    1.18
    igne
    1.18
    itol
    1.14
    odka
    1.13
    inson
    1.13
    ulnerability
    1.11
    innie
    1.11
    Activations Density 0.029%

    No Known Activations