© 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. 14485
    Prev
    Next
    INDEX
    Explanations

    interactions related to getting a license

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to interactions involving authority or requests for action

    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
     anecd
    -0.65
    anticipated
    -0.64
    pmwiki
    -0.63
     unsurprisingly
    -0.60
     concluding
    -0.60
     keynote
    -0.60
    ministic
    -0.60
     convergence
    -0.58
     unveiling
    -0.57
     adaptation
    -0.57
    POSITIVE LOGITS
    !'"
    0.94
     ain
    0.88
     nig
    0.87
    ,'"
    0.84
    ',"
    0.84
     fuckin
    0.83
    '"
    0.82
     âĢ¦"
    0.82
    .'"
    0.80
     whore
    0.78
    Activations Density 0.570%

    No Known Activations