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. 3-RES-JB
    6. 10298
    Prev
    Next
    INDEX
    Explanations

    names associated with the name "Helen" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named Helen or Helena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickr
    -0.81
    iddles
    -0.80
    âĵĺ
    -0.75
    aign
    -0.74
    Discussion
    -0.73
    irements
    -0.73
    ngth
    -0.73
    emonium
    -0.73
    atory
    -0.71
    intelligence
    -0.71
    POSITIVE LOGITS
     Helen
    0.95
     Keller
    0.86
     Cald
    0.78
     Sloan
    0.76
    sea
    0.75
    terness
    0.71
    wig
    0.69
     Suz
    0.69
    ship
    0.68
    bestos
    0.68
    Activations Density 0.013%

    No Known Activations