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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 14610
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or criminal matters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vault" and its variations, as well as related terms like "fault."

    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
    gdala
    -0.80
    glers
    -0.78
    TERN
    -0.76
     straw
    -0.74
    atown
    -0.71
     Flavoring
    -0.71
    à¥
    -0.68
    ×IJ
    -0.68
    ALE
    -0.67
    pun
    -0.67
    POSITIVE LOGITS
    ault
    1.15
    aults
    1.00
    eus
    0.86
    lain
    0.79
    essor
    0.78
    iliary
    0.78
    ier
    0.76
    naire
    0.74
    ilege
    0.72
    pedia
    0.70
    Activations Density 0.009%

    No Known Activations