© 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. 4-RES-JB
    11. 24487
    Prev
    Next
    INDEX
    Explanations

    numbers related to ages or years

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in texts

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

    No Comments

    Negative Logits
     retard
    -0.83
     nutrient
    -0.78
     entitle
    -0.75
     wre
    -0.71
    olicy
    -0.71
     nuts
    -0.70
     pale
    -0.70
     parity
    -0.70
    irds
    -0.69
     inund
    -0.67
    POSITIVE LOGITS
    sic
    1.57
    formerly
    1.36
    pictured
    1.29
    aka
    1.27
    ?)
    1.25
    via
    1.22
    ...)
    1.17
    !)
    1.16
    which
    1.16
    emphasis
    1.14
    Activations Density 0.192%

    No Known Activations