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. 21817
    Prev
    Next
    INDEX
    Explanations

    mentions of food, particularly sushi and tacos

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific types of food, particularly sushi and tacos, as well as references to the Somali community

    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
     Lambert
    -1.02
     Dud
    -0.93
     Holland
    -0.88
     Falk
    -0.84
     Engel
    -0.82
     Hart
    -0.81
     bourgeois
    -0.79
     Feld
    -0.79
     Bernstein
    -0.79
    zek
    -0.78
    POSITIVE LOGITS
     sushi
    2.41
     tacos
    2.27
     taco
    2.24
     Taco
    2.01
     Somali
    1.71
     Somalia
    1.52
     tuna
    1.41
     salsa
    1.38
    ushi
    1.35
     Tac
    1.24
    Activations Density 0.066%

    No Known Activations