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. 8-RES-JB
    6. 19682
    Prev
    Next
    INDEX
    Explanations

    statements between "Ċ" and "<end>" markers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of reports or references to government actions and decisions

    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
     Printing
    -0.60
     Ancients
    -0.59
     Psy
    -0.58
     Squadron
    -0.58
     Unic
    -0.58
    atility
    -0.57
     Linux
    -0.57
     Trog
    -0.56
     Inquisition
    -0.56
     lookout
    -0.56
    POSITIVE LOGITS
    advertisement
    1.29
    Article
    1.14
    Advertisement
    1.06
    ³³³³³³³³
    1.04
    ³³³³
    0.92
    ³³³³³³³³³³³³³³³³
    0.92
    ³³³
    0.87
    posted
    0.79
    Posted
    0.75
    AMY
    0.75
    Activations Density 0.446%

    No Known Activations