© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 17611
    Prev
    Next
    INDEX
    Explanations

    the specific word "time" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal expressions or the concept of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.84
    ancial
    -0.77
    ortium
    -0.75
    warts
    -0.65
     platoon
    -0.64
    ging
    -0.63
    ourt
    -0.62
    ebted
    -0.61
    rosis
    -0.61
    raltar
    -0.61
    POSITIVE LOGITS
    frames
    0.81
    ZI
    0.75
    spe
    0.68
    IAS
    0.65
    liest
    0.63
    EMS
    0.63
     frame
    0.62
    code
    0.61
    zone
    0.59
    é¾į
    0.59
    Activations Density 0.031%

    No Known Activations