© 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. 10-RES-JB
    11. 13664
    Prev
    Next
    INDEX
    Explanations

    references to specific days or times

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "a" followed by descriptive terms or adjectives

    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
    ties
    -0.70
     answers
    -0.69
    upon
    -0.66
     unions
    -0.63
    Answer
    -0.61
    lords
    -0.61
    anova
    -0.60
     Presence
    -0.58
    adiq
    -0.58
     reacts
    -0.58
    POSITIVE LOGITS
     whim
    1.17
     dime
    1.01
     pedest
    0.95
     scale
    0.93
     treadmill
    0.89
     stret
    0.89
     continent
    0.84
     leash
    0.82
     nightly
    0.80
     daily
    0.79
    Activations Density 0.079%

    No Known Activations