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. 6-RES-JB
    6. 6477
    Prev
    Next
    INDEX
    Explanations

    names of cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "New" in various contexts, particularly related to location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.87
    ONSORED
    -0.84
    xual
    -0.83
    ILA
    -0.71
    alkyrie
    -0.71
    acebook
    -0.68
    ufact
    -0.68
    poke
    -0.68
    pless
    -0.67
    abetic
    -0.67
    POSITIVE LOGITS
    foundland
    1.21
    bies
    1.19
    bie
    1.18
     York
    1.13
     Zealand
    1.12
     Orleans
    1.02
     arrivals
    1.00
     Hampshire
    0.95
    castle
    0.95
     YORK
    0.94
    Activations Density 0.054%

    No Known Activations