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. 7186
    Prev
    Next
    INDEX
    Explanations

    names of people and formal organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly names and organizations

    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
     conclud
    -0.59
     Vaugh
    -0.53
     hindsight
    -0.52
     fray
    -0.51
    icipated
    -0.50
    idious
    -0.49
    aum
    -0.48
     rall
    -0.48
    neau
    -0.47
    ilers
    -0.47
    POSITIVE LOGITS
    ibrary
    0.52
    channelAvailability
    0.51
     Caps
    0.49
     glands
    0.46
    à¨
    0.46
     hus
    0.46
    oxide
    0.46
    icht
    0.45
     husband
    0.45
    Scot
    0.43
    Activations Density 1.456%

    No Known Activations