© 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. 8-RES-JB
    11. 13093
    Prev
    Next
    INDEX
    Explanations

    adjectives describing quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism or analysis of individuals in positions of authority

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Hidden
    -0.64
    utenberg
    -0.61
     Werner
    -0.60
     amazed
    -0.60
    oute
    -0.59
     mosa
    -0.59
     bubbles
    -0.58
     overload
    -0.57
    ahime
    -0.56
     frustrations
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.37
    soever
    1.04
     imaginable
    1.03
     EVER
    0.97
     slightest
    0.97
     remotely
    0.96
    ever
    0.95
     anymore
    0.94
    nor
    0.92
    etheless
    0.89
    Activations Density 0.280%

    No Known Activations