© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    mentions of honors or awards

    oai_token-act-pair · gpt-3.5-turbo

    words related to commendation or honors

    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
     Spray
    -0.79
     Franch
    -0.72
     overl
    -0.66
    TY
    -0.63
    TPS
    -0.63
    myra
    -0.62
     Prin
    -0.62
     Crowley
    -0.62
     Alz
    -0.61
     Workers
    -0.61
    POSITIVE LOGITS
    olulu
    1.39
    orable
    1.26
    esty
    1.19
    ours
    1.09
    ored
    1.02
    oured
    1.02
    orem
    0.99
    ouring
    0.97
    oring
    0.97
    ouri
    0.90
    Activations Density 0.036%

    No Known Activations