© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    instances of the word "finds" followed by any word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    the verb "find" and its various contexts in sentences

    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
    creen
    -0.63
     mandatory
    -0.61
    roud
    -0.59
     Haste
    -0.57
     <[
    -0.57
    ollo
    -0.56
     buff
    -0.55
    medium
    -0.54
     BS
    -0.53
     strict
    -0.53
    POSITIVE LOGITS
     finds
    3.32
     discovers
    2.09
     find
    1.76
    find
    1.75
    Find
    1.59
     Find
    1.58
     sees
    1.55
     found
    1.50
     learns
    1.48
     finding
    1.47
    Activations Density 0.014%

    No Known Activations