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. 13116
    Prev
    Next
    INDEX
    Explanations

    mentions of or related to passers-by

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups of people, particularly in contexts related to interaction or observation

    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
    undo
    -0.70
    ested
    -0.68
     Forbidden
    -0.66
     Heads
    -0.62
    arians
    -0.60
     Cay
    -0.58
     Rape
    -0.58
    ansion
    -0.57
     Hare
    -0.57
     Pione
    -0.57
    POSITIVE LOGITS
    ages
    1.01
    by
    0.95
    atures
    0.94
    lihood
    0.89
    age
    0.85
    bly
    0.76
    bys
    0.75
     passer
    0.73
    iors
    0.71
    iper
    0.70
    Activations Density 0.054%

    No Known Activations