© 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 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. 7-RES-JB
    11. 20595
    Prev
    Next
    INDEX
    Explanations

    instances where the word "well" is used as an adverb to express approval or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    the word "well" indicating approval or quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongyang
    -0.78
    ription
    -0.75
    omore
    -0.71
    kefeller
    -0.67
    ngth
    -0.67
    apixel
    -0.66
    hip
    -0.66
    İĭ
    -0.65
    ategory
    -0.65
    rush
    -0.64
    POSITIVE LOGITS
    enough
    0.84
     dunno
    0.74
    come
    0.74
    esley
    0.72
     enough
    0.70
    spring
    0.69
    nah
    0.67
     behaved
    0.67
    entimes
    0.66
     Enough
    0.63
    Activations Density 0.023%

    No Known Activations