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. 2-RES-JB
    6. 3688
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations, particularly emphasizing the name "Shah."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Shah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Referred
    -0.71
    ctory
    -0.70
    anwhile
    -0.68
     Scient
    -0.68
     Camden
    -0.67
    ensation
    -0.67
    ument
    -0.65
    worldly
    -0.65
     Wilmington
    -0.65
     Skydragon
    -0.65
    POSITIVE LOGITS
     Shah
    1.00
    aji
    0.97
    ini
    0.86
    abal
    0.82
    ulk
    0.81
     Malik
    0.79
    ura
    0.78
    qi
    0.78
    olics
    0.78
    ahs
    0.77
    Activations Density 0.007%

    No Known Activations