© 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. 1-RES-JB
    11. 18655
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hol" followed by a number, potentially related to "holiday", "holidays", or a similar concept

    oai_token-act-pair · gpt-3.5-turbo

    the term "hol" and its variations related to holiday themes or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EED
    -0.77
     unauthorized
    -0.74
     fierce
    -0.65
    AGES
    -0.62
    XL
    -0.60
    FUL
    -0.60
    Rush
    -0.60
     shareholder
    -0.59
    INS
    -0.58
     ESV
    -0.57
    POSITIVE LOGITS
    idays
    1.27
    ocaust
    1.20
    iday
    1.05
    stery
    1.01
    hol
    1.00
    ocene
    0.98
    oho
    0.95
    sten
    0.90
    otom
    0.89
    stad
    0.86
    Activations Density 0.005%

    No Known Activations