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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 15280
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific character or entity represented by a symbol

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity named "J," particularly in the context of their activities or contributions

    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
    è¦ļéĨĴ
    -0.82
    atcher
    -0.82
    ngth
    -0.77
    enburg
    -0.76
    ammy
    -0.73
    estation
    -0.73
     implant
    -0.72
    unciation
    -0.72
     harvesting
    -0.71
    etts
    -0.70
    POSITIVE LOGITS
    BLE
    0.95
    VEN
    0.91
    CEPT
    0.90
    BOOK
    0.88
    ׾
    0.84
    BUS
    0.82
    ×ķ
    0.82
    IX
    0.81
    terday
    0.81
    ãĥŃ
    0.79
    Activations Density 0.013%

    No Known Activations