© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4202
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that indicate the action of acquiring new knowledge or skills

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "learn" in various contexts

    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
     caps
    -0.62
     insol
    -0.61
     imminent
    -0.60
    azo
    -0.60
     warrants
    -0.58
     Presidential
    -0.57
     approval
    -0.56
    itution
    -0.54
     cou
    -0.54
    flation
    -0.54
    POSITIVE LOGITS
     learn
    3.30
    learn
    2.39
     learns
    2.27
     Learn
    2.11
     learning
    2.11
     learnt
    2.09
    Learn
    2.02
     learned
    2.00
    learning
    1.77
    Learning
    1.70
    Activations Density 0.019%

    No Known Activations