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. 8-RES-JB
    6. 2912
    Prev
    Next
    INDEX
    Explanations

    questions or statements asking about reasoning or actions

    oai_token-act-pair · gpt-3.5-turbo

    requests for assistance and expressions of obligation or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himself
    -0.66
    ranged
    -0.65
     herself
    -0.65
    Pain
    -0.62
    Downloadha
    -0.59
     Digest
    -0.58
     guiActiveUn
    -0.56
     overshadowed
    -0.56
    elf
    -0.56
    ORY
    -0.56
    POSITIVE LOGITS
     ourselves
    2.20
     our
    1.26
     OUR
    0.96
     ours
    0.94
    assies
    0.76
    Our
    0.74
     THEM
    0.70
     collectively
    0.70
     Our
    0.69
    etimes
    0.69
    Activations Density 0.889%

    No Known Activations