© 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. 1093
    Prev
    Next
    INDEX
    Explanations

    phrases with adjectives and adverbs indicating intensity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers and degree modifiers that emphasize qualities 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
    liest
    -0.90
    cius
    -0.78
    ciating
    -0.77
    bringing
    -0.76
    ickr
    -0.75
    _.
    -0.71
    onnaissance
    -0.71
    ulia
    -0.70
     Bearing
    -0.69
    ring
    -0.68
    POSITIVE LOGITS
     quaint
    0.84
     alike
    0.82
     cozy
    0.81
     futuristic
    0.80
     smug
    0.80
     ominous
    0.80
     feminine
    0.79
     comfortable
    0.79
     alien
    0.79
     normal
    0.78
    Activations Density 0.103%

    No Known Activations