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. 16281
    Prev
    Next
    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to time and specific moments

    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
     fid
    -0.71
     defic
    -0.70
    eware
    -0.69
    soDeliveryDate
    -0.69
    ady
    -0.69
     ensures
    -0.68
     enables
    -0.67
    atile
    -0.66
     continuum
    -0.66
     advoc
    -0.66
    POSITIVE LOGITS
    Had
    1.09
    Was
    1.00
     Was
    0.97
     Didn
    0.96
    Instead
    0.96
     Instead
    0.95
     Turns
    0.91
     Had
    0.88
     Were
    0.84
    didn
    0.82
    Activations Density 0.870%

    No Known Activations