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. 9109
    Prev
    Next
    INDEX
    Explanations

    the name "Issa" within text

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of specific names or surnames

    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
    pering
    -0.79
     toget
    -0.70
    pered
    -0.65
     Simulation
    -0.63
     NR
    -0.63
     sque
    -0.62
    Role
    -0.61
     strut
    -0.61
     Eps
    -0.61
     Sporting
    -0.60
    POSITIVE LOGITS
    issa
    2.72
    leen
    2.27
    iza
    1.62
    uren
    1.58
    aghan
    1.57
    inda
    1.43
    osi
    1.34
    ureen
    1.28
    raine
    1.19
    ydia
    1.16
    Activations Density 0.018%

    No Known Activations