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. 0-RES-JB
    6. 9308
    Prev
    Next
    INDEX
    Explanations

    times of day expressed in hours and minutes, specifically focusing on evening times

    oai_token-act-pair · gpt-3.5-turbo

    references to specific times of day

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     belonging
    -0.67
     defense
    -0.66
     Iro
    -0.66
     Lands
    -0.63
     lands
    -0.61
     Dalai
    -0.61
     Contra
    -0.61
     invent
    -0.60
     Alaska
    -0.60
     Idaho
    -0.60
    POSITIVE LOGITS
    pm
    3.62
    PM
    2.43
     pm
    2.22
     PM
    1.78
    am
    1.52
    ps
    1.33
    fm
    1.33
    pd
    1.28
    pc
    1.28
    psc
    1.20
    Activations Density 0.017%

    No Known Activations