Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11174
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly with the last name "Andrews."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Andrews" in various contexts

    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
    ship
    -0.71
     terr
    -0.70
     Void
    -0.66
     veget
    -0.64
     vegetarian
    -0.63
     stud
    -0.63
     pocket
    -0.62
     trader
    -0.62
     positional
    -0.62
    LG
    -0.61
    POSITIVE LOGITS
     Andrews
    4.15
     Cummings
    1.28
    Andrew
    1.26
     Bowen
    1.21
     Higgins
    1.10
     Edwards
    1.10
     McGu
    1.10
     Michaels
    1.05
     Newman
    1.03
     Andrew
    1.03
    Activations Density 0.017%

    No Known Activations