© 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. 6-RES-JB
    11. 10772
    Prev
    Next
    INDEX
    Explanations

    names or references related to the person or character "Halle" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "alle" and similar-sounding variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icum
    -0.95
    ascus
    -0.88
    essions
    -0.81
    iaries
    -0.79
    etheless
    -0.79
    ocre
    -0.77
    icient
    -0.76
    ilon
    -0.74
    asive
    -0.72
    aido
    -0.72
    POSITIVE LOGITS
    tto
    1.12
    WER
    0.94
    tta
    0.94
    xual
    0.88
    phant
    0.76
    tti
    0.73
    mann
    0.73
    bucks
    0.71
     Sorce
    0.70
    gre
    0.70
    Activations Density 0.059%

    No Known Activations