© 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. 0-RES-JB
    11. 1103
    Prev
    Next
    INDEX
    Explanations

    phrases related to significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "meaning."

    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
    kees
    -0.71
    tub
    -0.63
    hurst
    -0.62
    ried
    -0.62
    Preview
    -0.61
    robe
    -0.60
    dl
    -0.58
    icipated
    -0.57
    abbit
    -0.57
    amin
    -0.57
    POSITIVE LOGITS
     meaning
    3.97
    meaning
    2.76
     Meaning
    2.60
     meanings
    2.44
     significance
    1.53
     signific
    1.48
     purpose
    1.18
     definition
    1.04
     symbolism
    1.03
     relevance
    1.02
    Activations Density 0.019%

    No Known Activations