© 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. 8-RES-JB
    11. 17240
    Prev
    Next
    INDEX
    Explanations

    proper names that contain the string "Ste" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter combination "Ste" and its variations in names

    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
     recip
    -0.66
    gdala
    -0.65
     skelet
    -0.64
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
    ADRA
    -0.63
     concess
    -0.62
    querque
    -0.61
     DRAG
    -0.61
    ãĥĥ
    -0.60
     substance
    -0.60
    POSITIVE LOGITS
    wagen
    0.91
    adder
    0.89
    bourg
    0.88
    tsy
    0.84
    heit
    0.77
    hess
    0.76
    rup
    0.75
    furt
    0.75
    helm
    0.75
    cil
    0.74
    Activations Density 0.207%

    No Known Activations