© 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. 12-RES-JB
    11. 2656
    Prev
    Next
    INDEX
    Explanations

    positive or negative adjectives to describe situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    contexts related to social and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hank
    -0.63
     KS
    -0.61
     SG
    -0.60
     PF
    -0.57
     Pegasus
    -0.57
     KC
    -0.54
     Pac
    -0.52
     Hue
    -0.52
     Miles
    -0.51
     Jesse
    -0.51
    POSITIVE LOGITS
     âĢ
    1.87
    »
    1.66
    ãĢį
    1.61
    [/
    1.52
    âĢ
    1.52
    ''
    1.50
    ãĢı
    1.50
     ÂŃ
    1.46
    ãĢ
    1.46
    âĻ¦
    1.35
    Activations Density 1.406%

    No Known Activations