© 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 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. 7-RES-JB
    11. 20617
    Prev
    Next
    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    never
    -0.70
    cause
    -0.66
     Io
    -0.66
    Pri
    -0.66
     Omega
    -0.65
    Case
    -0.63
    Mech
    -0.62
    Sport
    -0.62
    MJ
    -0.60
     Yamato
    -0.60
    POSITIVE LOGITS
     hiatus
    0.90
    dding
    0.76
    cation
    0.74
     trials
    0.71
     lapse
    0.71
     absence
    0.70
    iatus
    0.69
     reckoning
    0.69
     elapsed
    0.67
     exhausting
    0.67
    Activations Density 0.056%

    No Known Activations