© 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. 24300
    Prev
    Next
    INDEX
    Explanations

    mentions of branding, promotion, and marketing strategies

    oai_token-act-pair · gpt-3.5-turbo

    references to branding and products

    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
     extrad
    -0.65
    ensor
    -0.65
    utenant
    -0.63
    haired
    -0.62
    tein
    -0.61
     oneself
    -0.59
     Samar
    -0.57
     supervised
    -0.57
     superv
    -0.56
     briefed
    -0.55
    POSITIVE LOGITS
    mates
    0.98
     mates
    0.87
    ography
    0.86
     endeavors
    0.84
    é¾įåĸļ士
    0.84
     repertoire
    0.82
    ologies
    0.78
     counterparts
    0.78
     selves
    0.77
    ographies
    0.77
    Activations Density 0.441%

    No Known Activations