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. 11-RES-JB
    6. 15348
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Cu pertino"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Cupertino

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SPD
    -0.63
     Talent
    -0.62
     Bard
    -0.61
     congr
    -0.60
    nikov
    -0.59
     cred
    -0.59
     DEAD
    -0.58
     POLITICO
    -0.58
     Respons
    -0.58
     therape
    -0.58
    POSITIVE LOGITS
    isine
    1.39
    pees
    1.27
    pee
    1.22
    cca
    1.15
    issance
    1.12
    pert
    1.12
     Klux
    1.11
    esta
    1.11
    pport
    1.11
    cci
    1.10
    Activations Density 0.051%

    No Known Activations