Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 6842
    Prev
    Next
    INDEX
    Explanations

    names that contain "McC" along with related variations, such as "McCall" or "McClellan"

    oai_token-act-pair · gpt-3.5-turbo

    proper names, especially those related to individuals involved in political or military contexts

    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
    yip
    -0.95
    achev
    -0.69
     Galile
    -0.68
    drm
    -0.66
    terness
    -0.66
    ursday
    -0.66
    worldly
    -0.66
    ©¶æ
    -0.63
    gd
    -0.61
    ndra
    -0.60
    POSITIVE LOGITS
    area
    0.71
    abis
    0.71
    KY
    0.71
    estine
    0.70
    enna
    0.68
    inelli
    0.66
    cheon
    0.64
    pton
    0.64
    lish
    0.63
    urdy
    0.63
    Activations Density 0.112%

    No Known Activations