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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 61
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific name "Harry"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Harry" in various contexts

    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
    PsyNetMessage
    -0.83
    asio
    -0.71
    Filename
    -0.69
    PDATE
    -0.67
    IED
    -0.66
    76561
    -0.65
    yip
    -0.65
    PLA
    -0.62
    odcast
    -0.61
     commissioner
    -0.61
    POSITIVE LOGITS
     Potter
    1.44
    haus
    0.92
     Truman
    0.86
     Dresden
    0.80
     Hos
    0.77
     Harry
    0.77
     Fraz
    0.76
    phan
    0.76
    heter
    0.74
     Holmes
    0.73
    Activations Density 0.009%

    No Known Activations