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. 20245
    Prev
    Next
    INDEX
    Explanations

    references to types of food and ingredients

    oai_token-act-pair · gpt-3.5-turbo

    references to food items and recipes

    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
     AHL
    -0.62
     Ukrain
    -0.62
     ILCS
    -0.62
    lease
    -0.61
    sofar
    -0.60
    veyard
    -0.60
     Leafs
    -0.59
     compuls
    -0.59
     Dresden
    -0.58
     USL
    -0.58
    POSITIVE LOGITS
    Optional
    0.68
    BuyableInstoreAndOnline
    0.66
    Oracle
    0.60
     --------------------
    0.59
    è¦ļéĨĴ
    0.59
    wana
    0.59
    OTOS
    0.58
    cess
    0.57
    eg
    0.57
    nom
    0.56
    Activations Density 0.381%

    No Known Activations