© 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. 1-RES-JB
    11. 7060
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name or term "inem"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals in film or entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agers
    -0.75
    tip
    -0.70
    tips
    -0.66
    OPS
    -0.64
    Tip
    -0.64
     Pinterest
    -0.60
    atever
    -0.59
    ggies
    -0.59
     artificially
    -0.59
    ISH
    -0.58
    POSITIVE LOGITS
    inem
    1.57
     simultane
    0.80
     redes
    0.75
    mpeg
    0.75
    edia
    0.74
    ãĤ´ãĥ³
    0.74
     externalToEVAOnly
    0.74
    ONSORED
    0.74
    geist
    0.73
     unden
    0.73
    Activations Density 0.004%

    No Known Activations