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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 10430
    Prev
    Next
    INDEX
    Explanations

    references to prestigious institutions or awards

    oai_token-act-pair · gpt-3.5-turbo

    references to "Academy" and related institutions or awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meier
    -0.70
     palms
    -0.65
    vironment
    -0.65
    ppings
    -0.64
    ï¸ı
    -0.63
    _-
    -0.62
     Huckabee
    -0.61
    pd
    -0.60
    resp
    -0.59
    sheets
    -0.59
    POSITIVE LOGITS
     Academy
    1.11
     Awards
    0.97
     academy
    0.85
    emies
    0.84
     Award
    0.77
    rats
    0.77
    æ©
    0.76
    Blade
    0.73
    Grade
    0.73
     Supplement
    0.72
    Activations Density 0.010%

    No Known Activations