© 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. 8-RES-JB
    11. 3080
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is not as expected or negative in nature

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing negation or insignificance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLA
    -0.71
     caches
    -0.65
     Roots
    -0.65
     reper
    -0.64
    uctions
    -0.62
    rises
    -0.59
     downs
    -0.58
     floors
    -0.57
     openings
    -0.56
     emphasis
    -0.56
    POSITIVE LOGITS
    ĸļ
    0.99
    BuyableInstoreAndOnline
    0.76
    renheit
    0.74
     akin
    0.73
    lled
    0.69
    clud
    0.69
    ueller
    0.67
     extraord
    0.67
    dimensional
    0.66
    parable
    0.66
    Activations Density 0.139%

    No Known Activations