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. 9684
    Prev
    Next
    INDEX
    Explanations

    phrases related to time periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "during" in various contexts

    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
    ettle
    -0.83
    onica
    -0.81
    ovan
    -0.76
    adr
    -0.74
    amed
    -0.74
    ledged
    -0.73
    cloth
    -0.73
    iva
    -0.70
    ophe
    -0.68
    erie
    -0.67
    POSITIVE LOGITS
     periods
    1.21
     adolescence
    1.06
     infancy
    0.96
     wartime
    0.96
     renovations
    0.94
     daylight
    0.91
     weekends
    0.88
     Prohibition
    0.86
     eras
    0.85
     daytime
    0.84
    Activations Density 0.056%

    No Known Activations