Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12203
    Prev
    Next
    INDEX
    Explanations

    references to cookies, specifically focusing on actions involving cookies like making, eating, and tracking them

    oai_token-act-pair · gpt-3.5-turbo

    references to cookies, both as a food item and in a metaphorical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SI
    -0.71
    ashtra
    -0.70
    ities
    -0.68
    rior
    -0.64
    abouts
    -0.63
    orth
    -0.63
    WAYS
    -0.62
    ity
    -0.62
    ORN
    -0.62
    itate
    -0.62
    POSITIVE LOGITS
     cookies
    1.24
     dough
    1.09
     Clicker
    1.09
     cookie
    1.07
     jar
    1.01
     Cookies
    1.00
     Cookie
    0.97
    cookie
    0.96
     cutter
    0.95
     jars
    0.92
    Activations Density 0.015%

    No Known Activations