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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9279
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Anna"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Anna" and its variations

    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
     reload
    -0.74
     bullet
    -0.71
     copies
    -0.68
     bullets
    -0.66
     rot
    -0.66
     rotation
    -0.65
     rect
    -0.64
     shuff
    -0.61
     fluorescent
    -0.60
     engines
    -0.60
    POSITIVE LOGITS
    anna
    4.32
    annah
    2.01
    ana
    1.80
    ann
    1.72
    anne
    1.70
    anni
    1.56
    aina
    1.40
    anas
    1.21
    ANA
    1.17
    asta
    1.17
    Activations Density 0.011%

    No Known Activations