© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 2744
    Prev
    Next
    INDEX
    Explanations

    numeric values representing an increase or rise

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "risen" and its variations, indicating increases or growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ner
    -0.77
     Doc
    -0.65
     Crit
    -0.65
    DB
    -0.63
    hand
    -0.61
    Doc
    -0.61
     Koen
    -0.61
    Random
    -0.60
    db
    -0.59
     Gene
    -0.59
    POSITIVE LOGITS
     risen
    3.47
     rise
    1.74
     fallen
    1.68
     ascended
    1.64
     arisen
    1.59
     rose
    1.55
     rises
    1.52
     rising
    1.50
    rising
    1.49
     soared
    1.40
    Activations Density 0.012%

    No Known Activations