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. 10-RES-JB
    6. 18088
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names related to a certain ethnicity or culture

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Ian."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    door
    -0.81
     adolesc
    -0.74
    urers
    -0.68
    ridges
    -0.68
    urations
    -0.65
    URES
    -0.65
    Thirty
    -0.64
    olkien
    -0.64
    IVE
    -0.63
    DIV
    -0.63
    POSITIVE LOGITS
    nis
    1.30
    thus
    1.20
    apolis
    1.11
    na
    1.01
    akis
    0.96
    opolis
    0.96
    ity
    0.94
    throp
    0.93
    ova
    0.92
    ni
    0.90
    Activations Density 0.058%

    No Known Activations