© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 13469
    Prev
    Next
    INDEX
    Explanations

    mentions of special or unique things or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "special."

    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
    •Special

    No Comments

    Negative Logits
    nington
    -0.74
    amus
    -0.71
    hari
    -0.68
    latest
    -0.64
    shown
    -0.64
    anon
    -0.62
    yard
    -0.61
    Explore
    -0.61
    OTAL
    -0.61
    progress
    -0.60
    POSITIVE LOGITS
    ised
    1.37
    izations
    1.33
    ties
    1.26
    isations
    1.25
    ity
    1.11
    isation
    1.11
     relativity
    1.06
    ities
    1.05
    ising
    1.04
    ises
    1.04
    Activations Density 0.036%

    No Known Activations