© 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. 7-RES-JB
    11. 12620
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the process of learning or discovering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "learned" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abwe
    -0.74
    pei
    -0.66
    oided
    -0.64
    conn
    -0.64
    abases
    -0.64
    viks
    -0.63
    ataka
    -0.61
    rake
    -0.61
    phis
    -0.61
    idity
    -0.60
    POSITIVE LOGITS
     firsthand
    0.94
     lessons
    0.79
     Curve
    0.79
    llor
    0.79
     lesson
    0.78
     Learned
    0.78
     Teach
    0.76
     learnt
    0.75
    æĥ
    0.74
     humility
    0.73
    Activations Density 0.032%

    No Known Activations