© 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. 23963
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis on a specific detail or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to "the fact" or similar phrases indicating stated facts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.71
     livest
    -0.69
    avorite
    -0.67
     streng
    -0.66
    incinn
    -0.61
    ModLoader
    -0.59
    itton
    -0.57
     Flavoring
    -0.57
    dain
    -0.56
    atts
    -0.56
    POSITIVE LOGITS
    uality
    1.07
    ually
    1.05
    ional
    1.03
    orial
    0.94
     that
    0.86
    ual
    0.80
    oids
    0.78
    finder
    0.75
    oid
    0.74
    itious
    0.73
    Activations Density 0.036%

    No Known Activations