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. 21423
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities and terms, particularly related to "ND" (New Democracy) and the name "Alice."

    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
     Trophy
    -0.77
    ktop
    -0.76
     midrange
    -0.75
    flex
    -0.75
     Finder
    -0.74
     Batt
    -0.68
    icio
    -0.68
     champ
    -0.66
     Emmanuel
    -0.66
     squash
    -0.65
    POSITIVE LOGITS
    ND
    2.72
    Alice
    1.29
     Alice
    1.25
     Miranda
    1.19
     ND
    1.13
    iba
    1.06
     appropriations
    1.05
     ALEC
    1.03
    appropri
    1.02
     Appropriations
    1.00
    Activations Density 0.047%

    No Known Activations