© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5989
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating something uncommon or infrequent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rare" and its variations, indicating a focus on rarity or uncommonness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Andrews
    -0.63
     Bauer
    -0.62
     dismant
    -0.62
     Tens
    -0.60
     estab
    -0.59
     accordingly
    -0.56
    atever
    -0.56
     promptly
    -0.56
     devastated
    -0.55
     tatt
    -0.55
    POSITIVE LOGITS
    r
    1.09
    spect
    1.00
    st
    0.98
     occurrence
    0.96
    ty
    0.95
    fy
    0.89
    f
    0.89
     exceptions
    0.89
    istically
    0.87
    ries
    0.85
    Activations Density 0.045%

    No Known Activations