© 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. 10-RES-JB
    11. 13751
    Prev
    Next
    INDEX
    Explanations

    dates written in the format "February [day]"

    oai_token-act-pair · gpt-3.5-turbo

    dates, particularly in February

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opic
    -0.63
    achu
    -0.61
     cumbers
    -0.60
    kef
    -0.60
     behavi
    -0.59
    ioch
    -0.59
    ographed
    -0.56
     elephant
    -0.55
     delinquent
    -0.55
     parap
    -0.55
    POSITIVE LOGITS
    nd
    1.26
     Madness
    0.93
     2019
    0.92
     2017
    0.85
    ruary
    0.84
     2016
    0.84
     2018
    0.82
     2015
    0.81
    ricks
    0.81
    mber
    0.80
    Activations Density 0.022%

    No Known Activations