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. 22638
    Prev
    Next
    INDEX
    Explanations

    references to the location "Yonge Street" and surnames "Carey" and "Brunson"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, terms, and quantities related to people and objects

    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
    ouri
    -1.03
    agne
    -0.87
    iah
    -0.81
    areth
    -0.78
    ques
    -0.77
    iary
    -0.76
    ales
    -0.76
    iated
    -0.76
    igor
    -0.75
    ions
    -0.75
    POSITIVE LOGITS
    pillar
    0.76
     hitch
    0.74
    tten
    0.73
     docking
    0.72
     Clicker
    0.71
    leness
    0.71
    gger
    0.70
    theless
    0.70
     borough
    0.69
     captcha
    0.69
    Activations Density 0.037%

    No Known Activations