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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9164
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person or title, likely a character or show named "Sm" or "Smoky"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Sm" followed by various characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.83
     Cerberus
    -0.71
     Highlander
    -0.70
     Syl
    -0.65
    heit
    -0.65
     Tud
    -0.64
     Vanguard
    -0.64
    ITAL
    -0.63
     Ancients
    -0.63
     Defenders
    -0.61
    POSITIVE LOGITS
    ugg
    1.30
    oky
    1.27
    ooth
    1.23
    okers
    1.19
    iley
    1.18
    oked
    1.18
    oker
    1.17
    okes
    1.17
    oke
    1.16
    itten
    1.15
    Activations Density 0.009%

    No Known Activations