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. 1-RES-JB
    6. 24422
    Prev
    Next
    INDEX
    Explanations

    instances where the text discusses time periods in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or concepts within a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arius
    -0.80
    owl
    -0.78
    athering
    -0.77
    adelphia
    -0.67
    atron
    -0.66
    throp
    -0.64
    auder
    -0.63
    eno
    -0.62
     overflow
    -0.62
     haze
    -0.62
    POSITIVE LOGITS
     appell
    0.81
    olicy
    0.80
     trials
    0.73
    iments
    0.73
    sic
    0.70
    imental
    0.68
    ĸļ
    0.67
    utsche
    0.66
    CHAT
    0.65
    ijing
    0.64
    Activations Density 0.000%

    No Known Activations