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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 14207
    Prev
    Next
    INDEX
    Explanations

    terms related to government agencies or specific units within an organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental or organizational structures and their divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kaw
    -0.75
    Neal
    -0.70
    CLOSE
    -0.67
    nect
    -0.67
    Coll
    -0.66
    isc
    -0.65
    clusive
    -0.64
    rac
    -0.63
     cards
    -0.63
    iah
    -0.63
    POSITIVE LOGITS
     Directorate
    3.49
     Subcommittee
    1.44
     subcommittee
    1.43
     vein
    1.27
     Framework
    1.24
    ervatives
    1.06
    tein
    0.97
    obos
    0.91
    unts
    0.89
     Appropriations
    0.89
    Activations Density 0.055%

    No Known Activations