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. 7-RES-JB
    6. 14768
    Prev
    Next
    INDEX
    Explanations

    mentions of actions taken involving victims

    oai_token-act-pair · gpt-3.5-turbo

    references to victims and their treatment in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.80
     Built
    -0.72
     Lessons
    -0.70
    è¦ļéĨĴ
    -0.70
     Critics
    -0.69
     externalToEVAOnly
    -0.65
    Northern
    -0.64
    antle
    -0.63
    equality
    -0.63
     Ranked
    -0.62
    POSITIVE LOGITS
     herself
    0.83
     himself
    0.80
     whom
    0.80
     remorse
    0.74
     identifiable
    0.72
     immedi
    0.71
     identified
    0.70
     ENT
    0.69
     narr
    0.67
    doctor
    0.67
    Activations Density 0.615%

    No Known Activations