© 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. 4-RES-JB
    11. 10573
    Prev
    Next
    INDEX
    Explanations

    words related to something impressive or exceptional

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stunning" and its context in various phrases

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

    No Comments

    Negative Logits
    ©¶æ
    -1.03
    ppo
    -0.92
    uld
    -0.69
    ciplinary
    -0.68
    veyard
    -0.67
    claimer
    -0.67
    amins
    -0.65
    reprene
    -0.65
    appa
    -0.65
    pora
    -0.65
    POSITIVE LOGITS
    ly
    1.35
    LY
    1.04
    NESS
    0.82
    ingly
    0.81
     contrasts
    0.75
     stunning
    0.74
     revelations
    0.73
     revelation
    0.70
    ively
    0.69
    ulously
    0.69
    Activations Density 0.020%

    No Known Activations