© 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. 1-RES-JB
    11. 16440
    Prev
    Next
    INDEX
    Explanations

    the word "likelihood" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to likelihood and probability assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.85
    zac
    -0.76
    atro
    -0.76
    zeb
    -0.74
    agra
    -0.72
    oga
    -0.71
    cart
    -0.71
    avy
    -0.70
    unes
    -0.70
    bey
    -0.70
    POSITIVE LOGITS
    lihood
    1.29
     likelihood
    1.17
     odds
    0.98
     probability
    0.98
     unbeliev
    0.97
     guiActiveUn
    0.88
     belie
    0.88
     chances
    0.87
     probabilities
    0.87
    DragonMagazine
    0.85
    Activations Density 0.006%

    No Known Activations