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. 1072
    Prev
    Next
    INDEX
    Explanations

    references to various types of candy

    oai_token-act-pair · gpt-3.5-turbo

    references to candy and confectionery

    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
     NCT
    -0.69
    chron
    -0.68
     transcript
    -0.64
     transcription
    -0.63
     Chronicle
    -0.62
     Own
    -0.61
     VIEW
    -0.60
     Hutchinson
    -0.60
    Published
    -0.60
     Construct
    -0.59
    POSITIVE LOGITS
     candy
    1.26
     cane
    1.05
     sweets
    1.02
     Candy
    0.97
    mallow
    0.97
     cand
    0.90
     snacks
    0.83
     pudding
    0.83
     wra
    0.83
    fruit
    0.82
    Activations Density 0.008%

    No Known Activations