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. 3-RES-JB
    6. 10443
    Prev
    Next
    INDEX
    Explanations

    references to cookies

    oai_token-act-pair · gpt-3.5-turbo

    references to cookies, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igators
    -0.71
    SI
    -0.68
    WAYS
    -0.68
    abouts
    -0.67
    ctica
    -0.67
    ORN
    -0.66
    rolog
    -0.66
    involved
    -0.64
    idents
    -0.63
     Pharmaceutical
    -0.63
    POSITIVE LOGITS
     cookies
    1.33
     cookie
    1.15
    cookie
    1.07
     dough
    1.06
     Cookies
    1.02
     Cookie
    1.01
     jar
    1.00
     Clicker
    0.99
    Jar
    0.92
     cutter
    0.89
    Activations Density 0.009%

    No Known Activations