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. 10-RES-JB
    6. 23640
    Prev
    Next
    INDEX
    Explanations

    keywords related to a physical geographical feature - cliffs

    oai_token-act-pair · gpt-3.5-turbo

    references to cliffs and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ators
    -0.76
    Interstitial
    -0.73
    ates
    -0.71
    ative
    -0.70
    itution
    -0.68
    atives
    -0.68
    acity
    -0.68
    ufact
    -0.68
    ator
    -0.67
    IUM
    -0.67
    POSITIVE LOGITS
    driver
    1.02
    arding
    0.99
    arded
    0.92
    drivers
    0.90
    swer
    0.89
    estern
    0.89
    ritten
    0.88
    shoot
    0.88
    ses
    0.88
    cutting
    0.88
    Activations Density 0.092%

    No Known Activations