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. 23017
    Prev
    Next
    INDEX
    Explanations

    significant phrases indicating introspection or reflection

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events, times, and contextual details related to history or observations

    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
    NBA
    -0.59
     rightfully
    -0.58
    oÄŁan
    -0.56
     Remain
    -0.56
     uncond
    -0.55
     specifically
    -0.55
     unamb
    -0.54
    leneck
    -0.53
     essentially
    -0.53
    aganda
    -0.53
    POSITIVE LOGITS
    itiz
    0.66
     occurs
    0.65
     Aires
    0.65
    tarians
    0.64
    pires
    0.63
     happens
    0.62
    nces
    0.62
    ses
    0.62
    ishes
    0.62
    WARE
    0.61
    Activations Density 0.679%

    No Known Activations