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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11127
    Prev
    Next
    INDEX
    Explanations

    the name "Brittan"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, presumably "Lord Britt."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hook
    -0.85
    0002
    -0.83
    isSpecialOrderable
    -0.79
    Dub
    -0.69
    tenance
    -0.68
    reprene
    -0.67
    ptive
    -0.66
    font
    -0.66
    mouth
    -0.65
    sf
    -0.64
    POSITIVE LOGITS
    ohyd
    0.81
     GOODMAN
    0.76
    ALLY
    0.75
     mund
    0.69
    nect
    0.68
    ITION
    0.68
    inders
    0.68
     Cosponsors
    0.67
     Britt
    0.66
    perse
    0.65
    Activations Density 0.044%

    No Known Activations