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. 1-RES-JB
    6. 12374
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically last names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and entities relevant to the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hens
    -0.78
    hedral
    -0.77
    illion
    -0.76
     Ukrain
    -0.73
    emetery
    -0.70
    osate
    -0.69
    ertodd
    -0.69
    onent
    -0.68
    lez
    -0.68
    ic
    -0.67
    POSITIVE LOGITS
     Commodore
    0.85
    é¾įå
    0.74
     Neh
    0.71
     Wem
    0.71
     Barg
    0.70
     Holden
    0.70
     concess
    0.70
    selves
    0.69
     barg
    0.68
    wcsstore
    0.67
    Activations Density 0.023%

    No Known Activations