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. 23197
    Prev
    Next
    INDEX
    Explanations

    people or groups of people that are negatively impacted or under threat

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or relationships among individuals

    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
    cer
    -0.75
    ibrary
    -0.69
    WithNo
    -0.67
     oneself
    -0.67
    uve
    -0.66
    otos
    -0.62
    Ĥİ
    -0.61
    wcs
    -0.60
     itself
    -0.57
     guiName
    -0.57
    POSITIVE LOGITS
    hip
    1.30
    '
    1.25
    hips
    1.20
    mates
    1.04
     selves
    0.94
    ervative
    0.92
     counterparts
    0.90
    '-
    0.89
    hare
    0.89
    heet
    0.89
    Activations Density 0.163%

    No Known Activations