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. 10-RES-JB
    6. 11729
    Prev
    Next
    INDEX
    Explanations

    words related to locations or entities with the pattern "Sal-"

    oai_token-act-pair · gpt-3.5-turbo

    words relating to types of food, particularly those involving the term "salami"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.70
     Engels
    -0.70
     block
    -0.63
     brackets
    -0.61
    LINE
    -0.61
     bluff
    -0.60
     trace
    -0.59
    å¸
    -0.57
     Speedway
    -0.56
     cannon
    -0.55
    POSITIVE LOGITS
    uddin
    0.89
    pta
    0.85
     Cot
    0.78
    ão
    0.77
    ieri
    0.76
    encia
    0.76
    uala
    0.75
    ÃŃa
    0.75
    ahar
    0.73
    iland
    0.73
    Activations Density 0.193%

    No Known Activations