Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11909
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or statements

    oai_token-act-pair · gpt-3.5-turbo

    quotes or dialogue throughout the text

    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
     listed
    -0.79
     paired
    -0.75
     conj
    -0.72
     answering
    -0.72
     featured
    -0.71
     printers
    -0.70
     lining
    -0.70
     printer
    -0.69
     favor
    -0.69
     translating
    -0.68
    POSITIVE LOGITS
    Absolutely
    1.41
    Cause
    1.37
    Very
    1.33
    Extreme
    1.26
    Political
    1.23
    Nobody
    1.22
    Everybody
    1.21
    Interstitial
    1.21
    False
    1.18
    Nothing
    1.17
    Activations Density 0.038%

    No Known Activations