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. 9-RES-JB
    6. 22048
    Prev
    Next
    INDEX
    Explanations

    time periods within a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time periods and temporal data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xs
    -0.69
    optional
    -0.63
    egu
    -0.62
     extras
    -0.60
    atem
    -0.60
    icc
    -0.59
     kins
    -0.59
     instinct
    -0.58
    umbn
    -0.57
    inis
    -0.57
    POSITIVE LOGITS
    frames
    1.02
    frame
    0.81
     ending
    0.81
     ended
    0.80
     Ago
    0.80
     period
    0.80
     Gallup
    0.79
    pan
    0.78
     spanning
    0.77
     studied
    0.76
    Activations Density 0.219%

    No Known Activations