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. 20540
    Prev
    Next
    INDEX
    Explanations

    names containing the letters "us"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "us," indicating a focus on personal or collective pronouns related to inclusion or identity

    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
    ottest
    -0.72
    ITNESS
    -0.69
    regor
    -0.68
    GM
    -0.62
     payoff
    -0.61
     td
    -0.61
    rought
    -0.61
     runoff
    -0.60
    ACP
    -0.60
    RAG
    -0.59
    POSITIVE LOGITS
    pex
    1.14
    peed
    1.02
    cules
    1.00
    sein
    0.97
    pects
    0.96
    pect
    0.96
    pecting
    0.95
    hee
    0.92
    cular
    0.92
    CRIP
    0.92
    Activations Density 0.033%

    No Known Activations