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. 19171
    Prev
    Next
    INDEX
    Explanations

    specific times of day in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    specific time indicators in a narrative

    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
    ufact
    -0.71
    lessly
    -0.68
     prolifer
    -0.62
    saf
    -0.60
    sein
    -0.59
     Aure
    -0.56
    BILITIES
    -0.56
    hetically
    -0.55
     Parables
    -0.55
    hetic
    -0.54
    POSITIVE LOGITS
    pm
    1.38
     pm
    1.36
    PM
    1.22
     PM
    1.10
    AM
    1.09
    am
    0.99
     PST
    0.97
     PDT
    0.97
     AM
    0.96
     noon
    0.94
    Activations Density 0.040%

    No Known Activations