© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10626
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or distinctions between different categories or concepts

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words indicating contrast or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.76
    ngth
    -0.75
     Tears
    -0.75
    ttes
    -0.74
    amines
    -0.74
     chairs
    -0.72
    stanbul
    -0.70
    ulia
    -0.69
    oldemort
    -0.68
     Hew
    -0.66
    POSITIVE LOGITS
     otherwise
    1.12
     nons
    1.03
     unex
    0.99
     non
    0.95
     uns
    0.93
     passive
    0.92
     unprotected
    0.91
     nont
    0.90
     unin
    0.89
     conventional
    0.88
    Activations Density 0.120%

    No Known Activations