© 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. 12232
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing key concepts or principles

    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
    mares
    -0.92
    vernment
    -0.77
    hips
    -0.75
     Figures
    -0.72
    ells
    -0.71
    stellar
    -0.69
    RAW
    -0.68
    borough
    -0.67
    RAFT
    -0.67
    Staff
    -0.63
    POSITIVE LOGITS
     norm
    1.25
     safest
    1.14
     cornerstone
    1.12
     quickest
    1.09
     easiest
    1.09
     hallmark
    1.09
     cheapest
    1.06
     answer
    1.06
     antidote
    1.03
     essence
    1.02
    Activations Density 0.112%

    No Known Activations