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. 1-RES-JB
    6. 17416
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a person named Flaherty

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those involved in reporting or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nap
    -0.67
    PLA
    -0.65
    fighter
    -0.64
    changes
    -0.63
     Fighters
    -0.63
    Prot
    -0.62
     Corpus
    -0.62
    hist
    -0.62
    ventus
    -0.62
    pires
    -0.61
    POSITIVE LOGITS
    herty
    0.98
    ynski
    0.87
    shire
    0.84
    quist
    0.84
    issance
    0.80
    loo
    0.80
    sonian
    0.79
    uda
    0.79
    steen
    0.79
    stein
    0.76
    Activations Density 0.003%

    No Known Activations