© 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. 4-RES-JB
    11. 13490
    Prev
    Next
    INDEX
    Explanations

    references to various educational institutions, specifically schools and universities

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions, particularly schools

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãģį
    -0.80
     livest
    -0.79
    vernment
    -0.76
     dehyd
    -0.67
     Bundy
    -0.66
     exhaustion
    -0.65
     volatile
    -0.64
     distress
    -0.64
     flow
    -0.64
     likelihood
    -0.63
    POSITIVE LOGITS
    boy
    0.99
    girls
    0.97
    enium
    0.92
    lot
    0.90
    boys
    0.90
    uates
    0.90
     graduates
    0.88
    house
    0.86
    kids
    0.86
    essor
    0.86
    Activations Density 0.053%

    No Known Activations