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. 3016
    Prev
    Next
    INDEX
    Explanations

    government organizations and agencies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government agencies or bureaus

    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
    jad
    -0.78
    ients
    -0.74
    matter
    -0.73
    anchez
    -0.70
    wcs
    -0.68
    irs
    -0.68
    blance
    -0.68
    rises
    -0.68
    iour
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    POSITIVE LOGITS
     Excellence
    0.92
     Forestry
    0.88
     Inquiry
    0.86
     Alcohol
    0.85
     Statistics
    0.85
     Statistical
    0.83
     Shipping
    0.82
     Directors
    0.82
     Engineering
    0.81
     Economic
    0.81
    Activations Density 0.063%

    No Known Activations