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. 0-RES-JB
    6. 3253
    Prev
    Next
    INDEX
    Explanations

    references to a specific word "Ark."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Ark" and its various contexts throughout the text

    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
     diabetic
    -0.76
     diabetes
    -0.74
     sugars
    -0.73
     caffeine
    -0.73
     McMahon
    -0.70
     Thai
    -0.69
    weeney
    -0.68
    uff
    -0.68
     McMaster
    -0.67
    ugh
    -0.65
    POSITIVE LOGITS
     Ark
    4.16
    Ark
    2.92
     Neb
    1.21
     Arkansas
    1.10
    ARK
    1.06
     Ik
    1.06
     Exodus
    1.05
     Avatar
    1.04
     Shroud
    1.04
     Creation
    1.03
    Activations Density 0.015%

    No Known Activations