© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16093
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and documentation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of historical events and their contexts

    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
    Fax
    -0.76
    nesty
    -0.73
    amazon
    -0.72
    Safe
    -0.71
     waivers
    -0.69
    Tweet
    -0.68
     Beware
    -0.67
     Ratings
    -0.67
    safe
    -0.64
     cheap
    -0.63
    POSITIVE LOGITS
     eras
    1.46
     history
    1.39
    history
    1.37
     era
    1.31
     epoch
    1.28
     chronological
    1.25
     historical
    1.24
     period
    1.23
     histories
    1.22
     historians
    1.20
    Activations Density 0.725%

    No Known Activations