© 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. 24078
    Prev
    Next
    INDEX
    Explanations

    specific names or terms, potentially related to media or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon names or types

    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
    è¦ļéĨĴ
    -0.87
    ãģĨ
    -0.67
    MODE
    -0.66
    frames
    -0.64
     briefs
    -0.63
     Fn
    -0.62
     ESC
    -0.61
     impunity
    -0.60
     SHALL
    -0.59
     corrid
    -0.57
    POSITIVE LOGITS
    vertising
    1.26
    jamin
    1.19
    ropolitan
    1.14
    elaide
    1.14
    elligence
    1.12
    resa
    1.09
    roximately
    1.07
    ocolate
    1.06
    utsche
    1.06
    odore
    1.05
    Activations Density 0.241%

    No Known Activations