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. 10-RES-JB
    6. 10970
    Prev
    Next
    INDEX
    Explanations

    numerical values or currency-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical information or statistics related to various topics

    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
    insured
    -0.76
    eatures
    -0.76
    Ly
    -0.76
    conservancy
    -0.76
    ciplinary
    -0.75
    defense
    -0.74
    Grant
    -0.74
    sole
    -0.74
    Manchester
    -0.73
    stre
    -0.73
    POSITIVE LOGITS
     [+]
    1.04
     Discuss
    1.03
     Introduction
    1.02
     âĸ
    1.01
     Submit
    1.01
     ..........
    1.00
     ..............
    1.00
     âĨ
    0.98
     =================================================================
    0.98
    <|endoftext|>
    0.97
    Activations Density 0.112%

    No Known Activations