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. 8-RES-JB
    6. 17983
    Prev
    Next
    INDEX
    Explanations

    mentions of locations with the word "Mal" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the country "Malawi" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shutterstock
    -0.66
     pony
    -0.65
     Zup
    -0.64
    å£
    -0.64
    é¾įå¥ij士
    -0.64
    RANT
    -0.64
     Polo
    -0.64
    æĸ¹
    -0.63
    OME
    -0.61
    ARD
    -0.61
    POSITIVE LOGITS
    icious
    1.27
    colm
    1.16
    ignant
    1.16
    ibu
    1.13
    practice
    1.12
    adies
    1.12
    nutrition
    1.05
    pher
    1.04
    ayan
    1.01
    icia
    0.99
    Activations Density 0.020%

    No Known Activations