© 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. 0-RES-JB
    11. 12193
    Prev
    Next
    INDEX
    Explanations

    words related to a specific technology term

    oai_token-act-pair · gpt-3.5-turbo

    specific brand names or titles related to media and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imar
    -0.71
    gap
    -0.70
    ãĤŃ
    -0.70
     segreg
    -0.68
    gp
    -0.67
     Bulg
    -0.65
    ãĥĺ
    -0.64
    Ble
    -0.63
    umat
    -0.61
     Ake
    -0.61
    POSITIVE LOGITS
    OTT
    2.42
    ruff
    2.34
    RAW
    1.88
     Remix
    1.65
    OUS
    1.35
    arton
    1.31
    antle
    1.12
    ORN
    1.12
    usters
    1.03
     dos
    0.96
    Activations Density 0.034%

    No Known Activations