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. 21396
    Prev
    Next
    INDEX
    Explanations

    time-related references, specifically mentions of past events

    oai_token-act-pair · gpt-3.5-turbo

    references to time or past events

    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
    ittee
    -0.65
     Osc
    -0.65
    ittees
    -0.63
    entric
    -0.63
     Corpse
    -0.63
    inational
    -0.63
     haz
    -0.61
    ellen
    -0.61
    izo
    -0.58
     tyr
    -0.58
    POSITIVE LOGITS
    dated
    1.17
    stab
    1.12
    GROUND
    1.07
    packs
    1.07
    fires
    1.05
    packing
    1.04
    tracking
    1.00
    fired
    0.97
    haul
    0.93
    country
    0.92
    Activations Density 0.048%

    No Known Activations