© 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. 10-RES-JB
    11. 11041
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of learning or knowledge acquisition is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of learning

    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
    ãĥĨ
    -0.69
    een
    -0.68
    riot
    -0.67
    orescent
    -0.66
    govtrack
    -0.65
    inth
    -0.65
    bum
    -0.65
    zzi
    -0.63
    hao
    -0.63
    berus
    -0.63
    POSITIVE LOGITS
     how
    1.06
     lessons
    0.91
     about
    0.89
     firsthand
    0.89
     humility
    0.87
     lesson
    0.85
     Curve
    0.82
     calculus
    0.78
     ways
    0.76
     manners
    0.75
    Activations Density 0.048%

    No Known Activations