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. 7761
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rogers" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Rogers."

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.73
    /-
    -0.70
    spring
    -0.68
    fare
    -0.66
    visory
    -0.66
    itia
    -0.64
    ãĥł
    -0.64
    alogue
    -0.64
     Teresa
    -0.63
    sweet
    -0.62
    POSITIVE LOGITS
    loo
    1.09
     Rogers
    1.06
    tel
    0.93
    burgh
    0.92
    Tel
    0.87
    otiation
    0.83
    hiba
    0.81
    oshenko
    0.80
    dale
    0.79
    sonian
    0.76
    Activations Density 0.006%

    No Known Activations