© 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. 9413
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leaves" preceded by context words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "leaves."

    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
    PDATE
    -0.93
    anooga
    -0.73
    iscopal
    -0.72
    oÄŁ
    -0.70
     Cosponsors
    -0.69
    eatures
    -0.67
     concess
    -0.65
    owler
    -0.65
    ItemTracker
    -0.65
    MAT
    -0.64
    POSITIVE LOGITS
     Leaves
    0.96
     leaves
    0.93
    overs
    0.91
     litter
    0.85
    hift
    0.80
    pora
    0.76
    ophical
    0.72
    ffee
    0.71
    ings
    0.69
    metics
    0.68
    Activations Density 0.007%

    No Known Activations