© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    phrases denoting rules or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and practice a focus on defining and clarifying standards or expectations

    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
    rocket
    -0.60
    staking
    -0.59
     fec
    -0.58
    cision
    -0.57
     Pyramid
    -0.56
     ginger
    -0.55
     Dian
    -0.54
     assassination
    -0.54
    Adult
    -0.53
    enne
    -0.53
    POSITIVE LOGITS
     how
    1.07
     what
    1.03
     why
    0.96
     whats
    0.95
    what
    0.94
    why
    0.92
     shouldn
    0.89
     whence
    0.86
     where
    0.78
     WHY
    0.78
    Activations Density 0.075%

    No Known Activations