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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3250
    Prev
    Next
    INDEX
    Explanations

    the name "Alexander" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Alexander."

    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
     tub
    -0.78
    eals
    -0.75
    swing
    -0.75
     suc
    -0.71
     warped
    -0.70
    isec
    -0.68
    Switch
    -0.66
     Wii
    -0.66
     surf
    -0.66
     recy
    -0.65
    POSITIVE LOGITS
     Alexander
    3.64
    Alexander
    2.99
     ALE
    1.48
     Anton
    1.38
     Alexandra
    1.37
     Maced
    1.35
     Alex
    1.31
     Alexis
    1.24
     Igor
    1.23
     Darius
    1.22
    Activations Density 0.013%

    No Known Activations