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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 22586
    Prev
    Next
    INDEX
    Explanations

    medical conditions or complications that can arise in relation to treatments or actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'side effects'

    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
    Ĥİ
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    ORN
    -0.68
    æ©Ł
    -0.67
    ukong
    -0.67
    ogy
    -0.66
    rss
    -0.64
    ESCO
    -0.63
    nia
    -0.63
    ä¹ĭ
    -0.62
    POSITIVE LOGITS
    kick
    1.40
    burn
    1.17
    bars
    1.09
    real
    0.97
    car
    0.97
    chain
    0.96
    chains
    0.95
    bar
    0.92
    channel
    0.88
    effects
    0.88
    Activations Density 0.036%

    No Known Activations