© 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. 14446
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by "In" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the use of transition phrases or time markers in the text

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

    No Comments

    Negative Logits
    )))
    -0.74
    "},{"
    -0.74
    "}],"
    -0.69
    ullah
    -0.69
    Repeat
    -0.68
    ))))
    -0.68
     unfocusedRange
    -0.67
     Lastly
    -0.66
     ..."
    -0.65
    assad
    -0.64
    POSITIVE LOGITS
     starters
    0.74
    sofar
    0.74
     Pew
    0.72
     Gallup
    0.72
     industrialized
    0.71
    ccording
    0.67
     fact
    0.64
     polled
    0.63
    Consider
    0.63
     centuries
    0.62
    Activations Density 0.463%

    No Known Activations