Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 20701
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographical locations, specifically focusing on Slovenia, Slovakian, and Latter-Day Saints Church

    oai_token-act-pair · gpt-3.5-turbo

    references to Slovenia and specific organizations related to the Latter-day Saints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irlf
    -0.82
    ilitarian
    -0.76
    rough
    -0.75
    shock
    -0.75
    gee
    -0.75
    ãĤ§
    -0.70
    ulhu
    -0.69
    vertisements
    -0.69
    okia
    -0.67
    wash
    -0.67
    POSITIVE LOGITS
    lihood
    0.80
    owship
    0.75
    BuyableInstoreAndOnline
    0.71
    ĸļ
    0.69
    enses
    0.68
    Cro
    0.67
    enstein
    0.66
    erer
    0.65
     Sloven
    0.65
     Mamm
    0.65
    Activations Density 0.043%

    No Known Activations