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. 1-RES-JB
    6. 9601
    Prev
    Next
    INDEX
    Explanations

    proper names related to the name "Shah"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Shah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctory
    -0.71
     Wilmington
    -0.71
    ensation
    -0.67
     Scient
    -0.67
    ensional
    -0.67
     Referred
    -0.67
    ilater
    -0.67
     Camden
    -0.67
     Osc
    -0.65
     Hodg
    -0.65
    POSITIVE LOGITS
     Shah
    1.12
    aji
    0.96
    abal
    0.88
    ulk
    0.85
     Malik
    0.78
    vati
    0.77
     Meh
    0.77
    ini
    0.76
    qi
    0.75
    igans
    0.75
    Activations Density 0.005%

    No Known Activations