© 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. 3-RES-JB
    11. 668
    Prev
    Next
    INDEX
    Explanations

    mentions of something being revealed or exposed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Reve" or its variations, indicating a focus on a specific entity or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nadu
    -0.74
    ãĥ¼ãĥĨ
    -0.74
     eleph
    -0.64
     à¨
    -0.62
    etheless
    -0.61
    ONES
    -0.61
     famine
    -0.61
     Icelandic
    -0.61
    ucky
    -0.60
     FA
    -0.60
    POSITIVE LOGITS
    reve
    1.04
    cks
    1.01
    rence
    0.98
    llers
    0.95
    aled
    0.92
    port
    0.92
    ledged
    0.90
    esy
    0.89
    clus
    0.86
    lem
    0.86
    Activations Density 0.019%

    No Known Activations