© 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. 9-RES-JB
    11. 16027
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    dates or days of the week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     predec
    -0.58
     contr
    -0.53
     standard
    -0.53
     recourse
    -0.53
    Override
    -0.51
     steroids
    -0.51
     isolation
    -0.51
     indisp
    -0.49
    Ire
    -0.49
     naive
    -0.49
    POSITIVE LOGITS
    bush
    0.72
    actionDate
    0.70
    Reuters
    0.69
    ISON
    0.69
     ):
    0.69
     REUTERS
    0.67
    WASHINGTON
    0.65
    UTERS
    0.65
    utterstock
    0.62
     celebrates
    0.60
    Activations Density 0.194%

    No Known Activations