© 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. 16199
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical sensations or actions

    oai_token-act-pair · gpt-3.5-turbo

    articles and nouns that convey specific attributes or characteristics

    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
    eworks
    -0.79
    Sources
    -0.76
     annually
    -0.75
    ospons
    -0.70
     issues
    -0.70
    NAS
    -0.69
     investments
    -0.69
    Own
    -0.68
     Assets
    -0.67
    independent
    -0.67
    POSITIVE LOGITS
     roar
    1.21
     sudden
    1.21
     grin
    1.20
     flurry
    1.15
     smile
    1.12
     frantic
    1.10
     gasp
    1.08
     loud
    1.06
     faint
    1.05
     gust
    1.05
    Activations Density 0.256%

    No Known Activations