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. 3-RES-JB
    6. 19179
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating events from the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lua
    -0.84
    aspx
    -0.82
    ullivan
    -0.69
    unn
    -0.69
    ingham
    -0.68
    mble
    -0.68
    hw
    -0.68
    SIM
    -0.68
    Services
    -0.68
    handle
    -0.66
    POSITIVE LOGITS
     ago
    0.91
    opausal
    0.82
     mornings
    0.70
     sunset
    0.69
     graduation
    0.66
     Invalid
    0.66
    foundland
    0.65
    arians
    0.63
     canceled
    0.63
     retracted
    0.62
    Activations Density 0.022%

    No Known Activations