© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11291
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "barking"

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant actions or expressions of emotion in a narrative context

    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
    atism
    -0.68
     Skydragon
    -0.60
    awei
    -0.56
    ptions
    -0.55
    utenant
    -0.55
     Atomic
    -0.55
    abwe
    -0.54
    uador
    -0.53
     citizenship
    -0.53
    ativity
    -0.52
    POSITIVE LOGITS
    cause
    0.68
    Were
    0.64
    ente
    0.63
    lees
    0.63
    venge
    0.63
    Cause
    0.62
    Rail
    0.61
    shall
    0.61
    stri
    0.60
    fee
    0.60
    Activations Density 0.092%

    No Known Activations