© 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. 11424
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events or references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "history" and related concepts

    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
    igans
    -0.70
    vae
    -0.68
    oner
    -0.67
    autions
    -0.66
    enger
    -0.66
    leased
    -0.63
    ECA
    -0.63
    aton
    -0.62
    orc
    -0.62
    weeney
    -0.62
    POSITIVE LOGITS
     buffs
    1.12
     textbooks
    1.09
     lesson
    0.98
     books
    0.96
     repeats
    0.92
     repeating
    0.88
    orians
    0.82
     documentaries
    0.82
    making
    0.79
     museums
    0.77
    Activations Density 0.052%

    No Known Activations