© 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. 6-RES-JB
    11. 2977
    Prev
    Next
    INDEX
    Explanations

    names or words starting with "Sch"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sch"

    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
    -0.91
     censored
    -0.80
     constrained
    -0.71
     reborn
    -0.69
     futures
    -0.67
     Korra
    -0.65
     trickle
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.65
    DEN
    -0.64
     redundant
    -0.63
    POSITIVE LOGITS
    izoph
    1.32
    izophren
    1.22
    utz
    1.13
    acht
    1.12
    afer
    1.07
    nee
    1.04
    umann
    1.04
    uler
    1.02
    mitt
    1.01
    immer
    0.99
    Activations Density 0.011%

    No Known Activations