Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4082
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the word "vegan."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vegan"

    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
     handlers
    -0.72
     showers
    -0.71
    iewicz
    -0.66
     shower
    -0.61
     Parties
    -0.60
     hanging
    -0.60
     labels
    -0.59
     rook
    -0.58
     hiding
    -0.58
     artifacts
    -0.58
    POSITIVE LOGITS
    mber
    1.38
    ctors
    1.38
    gas
    1.32
    ggie
    1.24
    tted
    1.22
    ctive
    1.16
    ternity
    1.11
    gged
    1.11
    ter
    1.11
    gan
    1.10
    Activations Density 0.026%

    No Known Activations