© 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. 1-RES-JB
    11. 3769
    Prev
    Next
    INDEX
    Explanations

    the word "odds."

    oai_token-act-pair · gpt-3.5-turbo

    references to probability or likelihood in decision-making contexts

    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
    ASED
    -0.78
    Interstitial
    -0.77
    ASE
    -0.77
    asus
    -0.76
    export
    -0.71
    Adventure
    -0.71
    Application
    -0.68
    ains
    -0.68
    amiya
    -0.67
    raine
    -0.67
    POSITIVE LOGITS
     odds
    1.63
     relent
    0.80
     athlet
    0.79
     ratio
    0.77
     ratios
    0.73
    lihood
    0.72
     chances
    0.72
     underdog
    0.71
     probabilities
    0.69
     caut
    0.69
    Activations Density 0.009%

    No Known Activations