© 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. 22621
    Prev
    Next
    INDEX
    Explanations

    words related to being a part of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "part" with varying degrees of emphasis

    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
    incinn
    -0.73
    anche
    -0.69
     confir
    -0.65
    asu
    -0.63
     arms
    -0.62
    apons
    -0.61
    ternity
    -0.60
    opa
    -0.59
     shorts
    -0.58
    ministic
    -0.58
    POSITIVE LOGITS
     part
    0.81
    icularly
    0.80
    ICLE
    0.75
    ners
    0.74
    aldehyde
    0.70
    icular
    0.70
    uary
    0.67
    part
    0.67
     Payton
    0.66
    dated
    0.66
    Activations Density 0.042%

    No Known Activations