© 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. 1-RES-JB
    6. 1972
    Prev
    Next
    INDEX
    Explanations

    names, especially surnames

    oai_token-act-pair · gpt-3.5-turbo

    the last names of multiple individuals mentioned in the text

    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
     nominal
    -0.71
    efeated
    -0.64
     rigid
    -0.60
    endra
    -0.59
    uctor
    -0.59
    UAL
    -0.58
     behalf
    -0.57
     redu
    -0.57
    terms
    -0.57
    raints
    -0.55
    POSITIVE LOGITS
    berger
    1.54
    bach
    1.00
    wald
    0.91
    bilt
    0.89
    stein
    0.88
    roth
    0.86
    vill
    0.84
    heimer
    0.81
    kamp
    0.80
    berg
    0.79
    Activations Density 0.007%

    No Known Activations