© 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. 12834
    Prev
    Next
    INDEX
    Explanations

    specific instances where a person or thing fits a particular description or role

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "fit the bill" or similar expressions indicating suitability or relevance

    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
     downed
    -0.66
     wrest
    -0.63
    iger
    -0.63
    ãĥ£
    -0.62
     inciting
    -0.61
     awa
    -0.60
     payable
    -0.59
     refusing
    -0.59
     withheld
    -0.59
     fought
    -0.59
    POSITIVE LOGITS
     precon
    1.03
    Interstitial
    0.93
     criteria
    0.90
     neatly
    0.90
     snug
    0.88
     niche
    0.88
    ahime
    0.87
     mold
    0.86
     stereotype
    0.83
     nicely
    0.82
    Activations Density 0.160%

    No Known Activations