© 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. 3-RES-JB
    6. 13578
    Prev
    Next
    INDEX
    Explanations

    instances of the word "courage" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of courage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.93
    oval
    -0.74
    ramid
    -0.68
    fixed
    -0.64
    erm
    -0.64
    design
    -0.64
    majority
    -0.63
    terms
    -0.63
    washer
    -0.62
    hemat
    -0.62
    POSITIVE LOGITS
    ously
    1.32
     courage
    1.07
    uous
    0.84
    uously
    0.84
     bravery
    0.80
     inspiring
    0.77
    ous
    0.77
    FUL
    0.72
    isma
    0.72
    fulness
    0.71
    Activations Density 0.009%

    No Known Activations