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. 12-RES-JB
    6. 14702
    Prev
    Next
    INDEX
    Explanations

    words related to short-term matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to short documentaries or short-term content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gd
    -0.70
    itia
    -0.67
     Pact
    -0.67
     Compass
    -0.61
     Dawn
    -0.58
    ICAN
    -0.57
    iano
    -0.55
    ¢
    -0.54
     Gaia
    -0.54
    atically
    -0.54
    POSITIVE LOGITS
    sighted
    1.33
    comings
    1.22
    coming
    1.20
    ening
    1.17
    listed
    1.17
    falls
    1.15
    bread
    1.13
    changed
    1.10
    lived
    1.09
    changing
    1.05
    Activations Density 0.057%

    No Known Activations