© 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. 4-RES-JB
    11. 17263
    Prev
    Next
    INDEX
    Explanations

    mentions of specific universities or words related to education

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cre" in various contexts related to institutions and organizations

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

    No Comments

    Negative Logits
    enegger
    -0.83
    doms
    -0.79
    insula
    -0.76
    ãģ®éŃĶ
    -0.72
    DragonMagazine
    -0.72
    PsyNetMessage
    -0.71
     "$:/
    -0.68
    é¾įå
    -0.68
     retri
    -0.64
    uyomi
    -0.64
    POSITIVE LOGITS
     Cre
    1.21
    cker
    1.01
    ighton
    1.00
    eny
    0.97
    Cre
    0.90
    isin
    0.86
    vern
    0.86
    utz
    0.86
    zar
    0.84
     Dame
    0.81
    Activations Density 0.010%

    No Known Activations