© 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. 3239
    Prev
    Next
    INDEX
    Explanations

    names or words containing the character sequence 'ay'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'ay' in various contexts

    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
    ITIES
    -0.67
    >>\
    -0.64
    icide
    -0.63
    ITY
    -0.63
    ipeg
    -0.63
     Archdemon
    -0.61
     Klopp
    -0.60
     thumbs
    -0.59
     Daredevil
    -0.58
    Reviewer
    -0.58
    POSITIVE LOGITS
    nor
    1.08
    nard
    0.99
    uga
    0.98
    alde
    0.95
    enne
    0.93
    ega
    0.93
    von
    0.93
    ride
    0.91
    atana
    0.90
    alam
    0.90
    Activations Density 0.052%

    No Known Activations