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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10184
    Prev
    Next
    INDEX
    Explanations

    references to specific versions of the "Age of Ultron" movies

    oai_token-act-pair · gpt-3.5-turbo

    references to various "ages" or periods, specifically related to different contexts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chief
    -0.82
    bledon
    -0.79
     Bundy
    -0.76
    iguous
    -0.72
    atem
    -0.72
    aminer
    -0.71
    henko
    -0.70
     Cosponsors
    -0.69
    unal
    -0.69
    etsk
    -0.69
    POSITIVE LOGITS
    llan
    0.79
    Age
    0.79
     Inquisition
    0.78
     Age
    0.75
    ummies
    0.70
    span
    0.69
     cohorts
    0.67
    ugen
    0.65
     Journals
    0.65
     Warm
    0.64
    Activations Density 0.023%

    No Known Activations