© 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. 12651
    Prev
    Next
    INDEX
    Explanations

    mentions of superlatives or things that are the highest in value within a sentence or passage

    oai_token-act-pair · gpt-3.5-turbo

    references to the highest levels or rankings in various contexts

    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
     Prompt
    -0.70
     Canaver
    -0.63
     Lilly
    -0.62
    go
    -0.61
    ching
    -0.61
     Samoa
    -0.59
     Braun
    -0.59
     Regener
    -0.59
    agra
    -0.59
     Faust
    -0.59
    POSITIVE LOGITS
     bidder
    1.04
    hest
    0.87
     rated
    0.86
     pinnacle
    0.82
    iary
    0.79
     highest
    0.79
     concentrations
    0.74
    highest
    0.73
     highs
    0.73
     earners
    0.72
    Activations Density 0.015%

    No Known Activations