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. 20858
    Prev
    Next
    INDEX
    Explanations

    the name "Maher" in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Maher

    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
    ec
    -0.76
     Corporation
    -0.74
     imperial
    -0.73
     unic
    -0.71
     Titans
    -0.70
     VW
    -0.67
     atomic
    -0.66
    fecture
    -0.66
     Virgin
    -0.65
     Nashville
    -0.65
    POSITIVE LOGITS
     Maher
    3.90
    Ma
    1.61
    kson
    1.13
    pour
    1.03
     Salon
    1.01
     Hebdo
    1.00
     Kham
    0.98
    anan
    0.96
     Issa
    0.96
     Yiannopoulos
    0.95
    Activations Density 0.021%

    No Known Activations