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. 21263
    Prev
    Next
    INDEX
    Explanations

    mentions of specific roles or positions held by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by numerical expressions or descriptors of roles, ages, or experiences

    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
    ðĿ
    -0.76
    tons
    -0.74
    imates
    -0.73
    eworks
    -0.71
    iths
    -0.69
    encies
    -0.67
    NetMessage
    -0.67
    ayers
    -0.66
    ency
    -0.66
    ivable
    -0.65
    POSITIVE LOGITS
     teenager
    1.34
     youngster
    1.02
     kid
    1.02
     child
    1.01
     spectator
    0.99
     prisoner
    0.97
     clerk
    0.96
     waiter
    0.96
     consultant
    0.95
     youth
    0.95
    Activations Density 0.106%

    No Known Activations