© 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. 10194
    Prev
    Next
    INDEX
    Explanations

    the name "Te" followed by a number, possibly related to a specific individual or entity

    oai_token-act-pair · gpt-3.5-turbo

    the name "Te" followed by various identifiers or references in a list-based manner

    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
    ãĥ¼ãĥĨ
    -0.70
    ĸļ
    -0.67
     Icelandic
    -0.62
     ESA
    -0.61
    IFIED
    -0.61
     Tackle
    -0.59
    wagen
    -0.58
     flaw
    -0.57
    iewicz
    -0.57
     puzzles
    -0.57
    POSITIVE LOGITS
    achable
    1.40
    aching
    1.32
    levision
    1.25
    achers
    1.22
    acher
    1.19
    legram
    1.16
    eming
    1.16
    aches
    1.16
    legraph
    1.15
    lev
    1.14
    Activations Density 0.015%

    No Known Activations