Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 20566
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning something new or acquiring knowledge

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "learned" and its variations

    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
    size
    -0.74
     tilt
    -0.71
    NH
    -0.67
    pop
    -0.66
    burse
    -0.65
    url
    -0.64
     Issue
    -0.64
     entitle
    -0.62
    FX
    -0.60
    Support
    -0.59
    POSITIVE LOGITS
     learned
    3.61
     learnt
    2.91
     Learned
    2.50
    learn
    2.17
     learns
    2.05
     learn
    1.83
     learning
    1.63
    Lear
    1.63
     mastered
    1.55
     taught
    1.41
    Activations Density 0.022%

    No Known Activations