© 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. 2-RES-JB
    6. 13695
    Prev
    Next
    INDEX
    Explanations

    dates in the format 'dd:mm:yy' with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to specific date formats or time stamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mingham
    -0.70
    matic
    -0.69
     destro
    -0.68
    utherland
    -0.67
    ierrez
    -0.65
    thora
    -0.65
     Drawn
    -0.65
    ophical
    -0.65
    dinand
    -0.64
    APH
    -0.64
    POSITIVE LOGITS
     01
    1.09
     02
    1.07
     03
    1.00
     00
    0.99
     05
    0.96
     06
    0.94
     09
    0.93
     04
    0.89
     07
    0.87
     08
    0.85
    Activations Density 0.006%

    No Known Activations