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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating temporal sequence

    oai_token-act-pair · gpt-3.5-turbo

    sequential actions and events in narratives

    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
     currently
    -0.66
     formerly
    -0.61
     prior
    -0.61
     affair
    -0.60
     gorilla
    -0.59
     nowadays
    -0.58
     lately
    -0.57
     Earlier
    -0.56
     unlike
    -0.55
     today
    -0.55
    POSITIVE LOGITS
    EEK
    0.76
    maxwell
    0.73
     proceeded
    0.71
    bered
    0.68
    raq
    0.67
    leep
    0.67
    iphany
    0.67
    GGGG
    0.66
    AAAAAAAA
    0.66
    rosis
    0.66
    Activations Density 0.506%

    No Known Activations