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. 7-RES-JB
    6. 18341
    Prev
    Next
    INDEX
    Explanations

    sentences indicating confirmation, registration, or authentication

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the state of registration or existence of an entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hawai
    -0.72
     Franch
    -0.70
     Buenos
    -0.66
     Fernand
    -0.64
     senses
    -0.64
    shore
    -0.63
     Strait
    -0.63
     Founding
    -0.61
    ão
    -0.61
     congr
    -0.60
    POSITIVE LOGITS
     actually
    0.89
    Ĥİ
    0.88
    çī
    0.78
     outwe
    0.77
     probably
    0.76
    rael
    0.75
     unchanged
    0.75
     indeed
    0.74
    VAL
    0.73
    Nap
    0.72
    Activations Density 0.303%

    No Known Activations