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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 7640
    Prev
    Next
    INDEX
    Explanations

    words related to locations or entities named "Sth." where "th" can be any two characters

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or initialisms, particularly those starting with "St"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.66
    vernment
    -0.63
     deserts
    -0.62
     triangle
    -0.61
     prelim
    -0.60
    cffffcc
    -0.60
     scraps
    -0.57
     favors
    -0.55
     imperative
    -0.54
    riend
    -0.53
    POSITIVE LOGITS
    helm
    1.00
    wart
    0.89
    wick
    0.85
    wagen
    0.84
    gered
    0.81
    ggle
    0.81
    warts
    0.79
    ngth
    0.76
    adder
    0.75
    olph
    0.74
    Activations Density 0.112%

    No Known Activations