© 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. 11975
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating that something is improbable or not expected to happen

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unlikely."

    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
    ulative
    -0.85
    ravings
    -0.82
    ixed
    -0.77
    ocked
    -0.76
    ricted
    -0.73
    atered
    -0.73
    lang
    -0.71
    awed
    -0.71
    artney
    -0.70
    ocker
    -0.70
    POSITIVE LOGITS
    bably
    0.90
     unlikely
    0.88
     fortun
    0.81
     unanimous
    0.81
     improbable
    0.79
     unanim
    0.78
     underdog
    0.77
    cffff
    0.76
    icably
    0.76
     foul
    0.72
    Activations Density 0.008%

    No Known Activations