© 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. 11-RES-JB
    11. 1851
    Prev
    Next
    INDEX
    Explanations

    words related to pronunciation and word origins

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to pronunciation and language

    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
    orthy
    -0.67
    rift
    -0.61
    kefeller
    -0.60
     logistical
    -0.59
    rehensive
    -0.59
    MRI
    -0.59
    planned
    -0.59
    staking
    -0.59
    keye
    -0.57
    Roberts
    -0.57
    POSITIVE LOGITS
     verbs
    1.62
     noun
    1.61
     phrases
    1.49
     pronouns
    1.40
     adject
    1.38
     verb
    1.33
     slang
    1.32
     vowel
    1.31
     words
    1.29
     pronunciation
    1.28
    Activations Density 0.606%

    No Known Activations