© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22958
    Prev
    Next
    INDEX
    Explanations

    sentences mentioning gratitude and appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of commendation or celebration

    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
     antitrust
    -0.83
     compromises
    -0.74
     unamb
    -0.71
     deflation
    -0.70
     rational
    -0.70
     plaus
    -0.70
     evasion
    -0.69
     plausible
    -0.69
     thrott
    -0.69
     disputed
    -0.68
    POSITIVE LOGITS
     Volunte
    0.99
     Photography
    0.95
     THANK
    0.93
     Photographer
    0.90
    nesday
    0.89
     facebook
    0.83
    Congratulations
    0.81
     Instructor
    0.80
     photographer
    0.79
     Brittany
    0.78
    Activations Density 0.876%

    No Known Activations