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. 7-RES-JB
    6. 15110
    Prev
    Next
    INDEX
    Explanations

    people's names or other proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ij"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poppy
    -0.71
    ACTED
    -0.68
     interchangeable
    -0.63
     flux
    -0.63
    女
    -0.62
     additive
    -0.62
    yards
    -0.61
     bleach
    -0.59
     Ranger
    -0.57
    stock
    -0.57
    POSITIVE LOGITS
    ournal
    1.22
    eh
    1.11
    utsu
    1.08
    ohn
    0.95
    ean
    0.95
    unction
    0.91
    oji
    0.91
    unal
    0.88
    wark
    0.88
    iang
    0.87
    Activations Density 0.017%

    No Known Activations