© 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. 9-RES-JB
    11. 16542
    Prev
    Next
    INDEX
    Explanations

    instances of the word "well" that denotes a high degree or extent

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "well" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apixel
    -0.78
    omore
    -0.76
    ategory
    -0.70
    rely
    -0.70
    xual
    -0.66
    avorite
    -0.65
    hyde
    -0.64
    emonic
    -0.62
    atto
    -0.61
    ription
    -0.61
    POSITIVE LOGITS
    spring
    0.96
    enough
    0.89
     enough
    0.86
     vers
    0.85
    esley
    0.85
    past
    0.82
     overdue
    0.81
     Enough
    0.78
     intention
    0.76
     beyond
    0.75
    Activations Density 0.041%

    No Known Activations