Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17069
    Prev
    Next
    INDEX
    Explanations

    instances of the word "likelihood"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the likelihood or probability of an event occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cott
    -0.68
    chu
    -0.65
    sov
    -0.62
    iel
    -0.61
    ilk
    -0.61
     Edit
    -0.61
    ü
    -0.61
     »
    -0.60
    ush
    -0.57
     02
    -0.57
    POSITIVE LOGITS
     likelihood
    3.70
     probability
    2.50
    lihood
    1.90
     probabilities
    1.84
     chances
    1.77
     possibility
    1.74
     odds
    1.72
     chance
    1.61
     propensity
    1.47
     plaus
    1.34
    Activations Density 0.011%

    No Known Activations