© 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. 1194
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "grand."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "grand."

    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
    tics
    -0.89
     clipboard
    -0.78
    Byte
    -0.66
    xit
    -0.64
     Clothing
    -0.63
    ayers
    -0.62
    enable
    -0.62
    Issue
    -0.62
    otion
    -0.62
     Clip
    -0.61
    POSITIVE LOGITS
     grand
    3.84
    grand
    2.43
    Grand
    2.08
     Grand
    2.05
     grandchildren
    1.41
     grandma
    1.20
     grandson
    1.15
     granddaughter
    1.15
     grandmother
    1.14
     grandparents
    1.14
    Activations Density 0.005%

    No Known Activations