© 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. 6-RES-JB
    11. 11922
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with the word "Let"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that initiate proposals or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    existent
    -0.70
    natureconservancy
    -0.67
    PLIED
    -0.67
    Zen
    -0.66
    atana
    -0.65
     worshipped
    -0.65
     cumbers
    -0.63
     holiest
    -0.61
    ?????-
    -0.61
     Viking
    -0.60
    POSITIVE LOGITS
    itia
    1.12
    tering
    1.01
    ting
    0.97
    tered
    0.95
    icia
    0.92
    hetically
    0.77
    ters
    0.74
    cheon
    0.71
    semb
    0.68
    ogether
    0.68
    Activations Density 0.023%

    No Known Activations