© 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. 22502
    Prev
    Next
    INDEX
    Explanations

    verbs related to conceding or accepting defeat

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "concede" and its variations

    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
    GROUP
    -0.76
    tan
    -0.76
     includ
    -0.70
    seed
    -0.65
     sights
    -0.62
     Pastebin
    -0.61
    oen
    -0.61
    tra
    -0.61
    chn
    -0.61
     attent
    -0.60
    POSITIVE LOGITS
    ickets
    0.90
     defeat
    0.88
     concede
    0.81
     conceded
    0.80
    arium
    0.77
     conced
    0.76
    ities
    0.72
    ylon
    0.71
    essor
    0.68
    inet
    0.67
    Activations Density 0.011%

    No Known Activations