© 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. 10-RES-JB
    11. 1344
    Prev
    Next
    INDEX
    Explanations

    the word "single" followed by various contexts and phrasings

    oai_token-act-pair · gpt-3.5-turbo

    references to single-player experiences or mentions of "single" in various contexts

    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
    Downloadha
    -0.85
    raints
    -0.81
     Lauder
    -0.74
    æ©Ł
    -0.72
     Guerrero
    -0.69
    orsi
    -0.66
    maxwell
    -0.66
    ravings
    -0.64
    bda
    -0.64
    ITNESS
    -0.64
    POSITIVE LOGITS
    handedly
    1.57
    ton
    1.35
     minded
    1.03
     digit
    1.01
    player
    1.01
     digits
    0.99
     sided
    0.97
    minded
    0.97
     malt
    0.94
     handed
    0.92
    Activations Density 0.030%

    No Known Activations