© 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. 10-RES-JB
    11. 10080
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exclusivity or singularity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Not only" followed by related clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.80
    glass
    -0.67
    ller
    -0.67
    AGES
    -0.61
    pire
    -0.61
    ]-
    -0.60
    nect
    -0.60
    ashington
    -0.59
    Marginal
    -0.58
    Enlarge
    -0.56
    POSITIVE LOGITS
     does
    0.80
     did
    0.80
     because
    0.69
     do
    0.65
     physically
    0.63
    does
    0.63
     livest
    0.62
     Does
    0.62
     am
    0.61
    because
    0.60
    Activations Density 0.018%

    No Known Activations