© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17708
    Prev
    Next
    INDEX
    Explanations

    date and time information in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    numerical and date-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vre
    -0.83
    isconsin
    -0.71
     fres
    -0.71
    avorite
    -0.70
    fman
    -0.70
    ault
    -0.70
    undai
    -0.70
    lesh
    -0.69
    heed
    -0.69
    pecially
    -0.68
    POSITIVE LOGITS
     Unknown
    1.26
     TBD
    1.12
     Various
    1.02
     Runs
    1.02
     None
    0.96
     TBA
    0.96
     Approximately
    0.94
     Measures
    0.89
     ???
    0.89
     Introduced
    0.87
    Activations Density 0.075%

    No Known Activations