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. 8-RES-JB
    6. 23281
    Prev
    Next
    INDEX
    Explanations

    time-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with time durations or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dearly
    -0.75
    liest
    -0.74
    dale
    -0.65
    rower
    -0.62
    grave
    -0.60
    stained
    -0.60
    abee
    -0.59
    ursed
    -0.59
    dating
    -0.59
     boldly
    -0.57
    POSITIVE LOGITS
    %"
    1.05
     dozen
    1.02
    dozen
    0.97
     percent
    0.90
    %
    0.82
     miles
    0.79
     thous
    0.78
     thirds
    0.78
     minutes
    0.76
    cms
    0.76
    Activations Density 0.142%

    No Known Activations