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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6331
    Prev
    Next
    INDEX
    Explanations

    pronouns that refer to or indicate groups of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference people or groups

    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
     Anything
    -0.70
     Delicious
    -0.67
     Anyway
    -0.67
    CLE
    -0.62
     Bound
    -0.62
    Okay
    -0.61
     Apart
    -0.61
     Gothic
    -0.60
     Cape
    -0.60
     Glob
    -0.59
    POSITIVE LOGITS
     specialize
    1.13
     aspire
    1.03
     reside
    0.94
     participated
    0.93
     benefited
    0.93
     migrated
    0.91
     comprise
    0.90
     inhabit
    0.89
     compose
    0.89
     preceded
    0.89
    Activations Density 0.127%

    No Known Activations