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. 14524
    Prev
    Next
    INDEX
    Explanations

    numbers related to statistics or metrics

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

    numerical values or statistics related to events

    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
     scrut
    -0.76
     millenn
    -0.72
     nomine
    -0.72
     mayoral
    -0.70
    anooga
    -0.69
     affordability
    -0.68
     payoff
    -0.67
    agall
    -0.66
     gloom
    -0.66
     artisan
    -0.64
    POSITIVE LOGITS
     partName
    1.26
    792
    1.21
    992
    1.20
    688
    1.20
    888
    1.18
    752
    1.18
    296
    1.17
    952
    1.16
    896
    1.16
    648
    1.16
    Activations Density 0.057%

    No Known Activations