© 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. 8-RES-JB
    11. 17823
    Prev
    Next
    INDEX
    Explanations

    terms related to mountains, particularly those starting with "Mt"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific mountains and notable place names

    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
    makers
    -0.75
    fold
    -0.73
    maker
    -0.70
    staking
    -0.65
     OnePlus
    -0.65
    e
    -0.64
    weight
    -0.63
    ONES
    -0.62
    mie
    -0.60
    SHIP
    -0.60
    POSITIVE LOGITS
    emonic
    1.38
    awar
    1.03
    iferation
    0.96
    acca
    0.93
    uchin
    0.91
    umin
    0.89
    esta
    0.88
    elta
    0.84
    oka
    0.84
    adena
    0.83
    Activations Density 0.068%

    No Known Activations