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. 3431
    Prev
    Next
    INDEX
    Explanations

    names, specifically surnames ending with "roney" or "haney"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their roles or associations

    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
    wcs
    -0.71
    oulos
    -0.65
     flick
    -0.62
    nesday
    -0.61
    heric
    -0.61
     Perspective
    -0.61
    bley
    -0.60
    akeru
    -0.60
     puzz
    -0.59
    itiveness
    -0.59
    POSITIVE LOGITS
    sbm
    0.75
    abet
    0.73
    ItemImage
    0.72
    äºĶ
    0.71
    lah
    0.71
    ij士
    0.70
    gha
    0.67
    iple
    0.67
    nih
    0.65
    Quantity
    0.64
    Activations Density 0.208%

    No Known Activations