© 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. 2-RES-JB
    11. 24115
    Prev
    Next
    INDEX
    Explanations

    instances of the word "developed"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "developed" and its variations, indicating a focus on the concept of development or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    que
    -0.77
     Keeper
    -0.75
    lua
    -0.73
    cgi
    -0.71
    wait
    -0.70
    wered
    -0.69
    knife
    -0.69
    cise
    -0.68
    wa
    -0.68
    pir
    -0.65
    POSITIVE LOGITS
    developed
    0.92
     developed
    0.86
     develops
    0.82
     developing
    0.78
    irtual
    0.78
    urally
    0.77
     behavi
    0.75
    Ô
    0.73
     Seym
    0.71
     patents
    0.71
    Activations Density 0.020%

    No Known Activations