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. 10098
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Congress"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Congress

    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
     MM
    -0.72
     srf
    -0.65
     Sussex
    -0.63
    âķIJâķIJ
    -0.63
    imilar
    -0.62
     Britann
    -0.62
     999
    -0.61
    Var
    -0.61
    jiang
    -0.60
     Vertical
    -0.60
    POSITIVE LOGITS
    woman
    1.27
    ional
    1.14
    men
    0.93
    crit
    0.87
    ername
    0.82
    arians
    0.81
    member
    0.81
     appropriated
    0.80
    women
    0.75
    inition
    0.74
    Activations Density 0.022%

    No Known Activations