© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20961
    Prev
    Next
    INDEX
    Explanations

    references to chains or sequences of events happening in a particular order

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "chain"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Demand
    -0.68
    osate
    -0.66
    olulu
    -0.65
    racuse
    -0.63
    imates
    -0.62
    issance
    -0.61
    BAT
    -0.61
     "$:/
    -0.60
     League
    -0.59
    oat
    -0.59
    POSITIVE LOGITS
    alysis
    1.10
    mail
    1.06
     Reaction
    1.04
     reaction
    0.90
    link
    0.89
     triglycer
    0.89
    rings
    0.84
    wal
    0.81
    aws
    0.80
    loader
    0.78
    Activations Density 0.042%

    No Known Activations