© 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. 2-RES-JB
    11. 11701
    Prev
    Next
    INDEX
    Explanations

    words related to surrendering or submitting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sur" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itsch
    -0.78
    ovie
    -0.76
    endor
    -0.69
    ICAL
    -0.67
    hetti
    -0.67
    icals
    -0.67
    assetsadobe
    -0.66
    oresc
    -0.62
    APS
    -0.61
     Investors
    -0.61
    POSITIVE LOGITS
     sur
    0.93
    mounted
    0.88
    fer
    0.87
    sur
    0.81
     absor
    0.80
    geons
    0.80
    reys
    0.78
    mount
    0.77
    sum
    0.77
    fing
    0.75
    Activations Density 0.005%

    No Known Activations