Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17441
    Prev
    Next
    INDEX
    Explanations

    references to time related to the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically the word "past" and its frequency

    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
    lees
    -0.78
     Franch
    -0.78
    hyde
    -0.69
    racuse
    -0.67
    iquid
    -0.66
    },{"
    -0.65
    csv
    -0.64
    NEY
    -0.63
    ioned
    -0.63
    roller
    -0.63
    POSITIVE LOGITS
     decade
    1.41
    ebin
    1.34
     millennium
    1.06
     century
    1.05
     few
    1.04
     couple
    1.02
     decades
    1.02
     week
    1.01
     fortnight
    1.00
     generations
    0.96
    Activations Density 0.031%

    No Known Activations