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. 11-RES-JB
    6. 10937
    Prev
    Next
    INDEX
    Explanations

    locations in different cities

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrog
    -0.74
     assum
    -0.73
     fung
    -0.72
     siph
    -0.67
     ineffective
    -0.67
     majesty
    -0.66
     prey
    -0.65
     clo
    -0.65
     scal
    -0.64
     anat
    -0.64
    POSITIVE LOGITS
    Reuters
    1.70
    CBS
    1.65
    AP
    1.49
    CNN
    1.37
    CN
    1.33
    AFP
    1.30
    Market
    1.29
    Thom
    1.28
    NEWS
    1.25
    WW
    1.19
    Activations Density 0.024%

    No Known Activations