© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24069
    Prev
    Next
    INDEX
    Explanations

    variations of the word 'concede'

    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 @ 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
    seed
    -0.76
     sights
    -0.70
    GROUP
    -0.67
    PATH
    -0.67
    chn
    -0.65
    tra
    -0.64
    bin
    -0.62
    oen
    -0.62
     Pastebin
    -0.61
    opped
    -0.61
    POSITIVE LOGITS
     concede
    1.06
     conceded
    1.01
     conced
    0.97
     concedes
    0.89
     defeat
    0.88
    ickets
    0.84
    Pixel
    0.72
    itable
    0.69
     Wynne
    0.69
    ities
    0.68
    Activations Density 0.008%

    No Known Activations