© 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. 10357
    Prev
    Next
    INDEX
    Explanations

    abbreviations or short forms commonly found in written text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of thoughts or questions

    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
     bullish
    -0.66
    ascus
    -0.65
     intended
    -0.65
    ogen
    -0.65
    ogene
    -0.63
     shy
    -0.62
     exclusively
    -0.61
     brief
    -0.60
    imate
    -0.59
    Å«
    -0.59
    POSITIVE LOGITS
     Likewise
    1.50
     Similarly
    1.45
     Conversely
    1.43
     Secondly
    1.37
     Additionally
    1.36
     Meanwhile
    1.35
     Others
    1.31
     Alternatively
    1.27
     Then
    1.26
     Furthermore
    1.25
    Activations Density 0.608%

    No Known Activations