© 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. 4-RES-JB
    11. 15651
    Prev
    Next
    INDEX
    Explanations

    the name "Gemma" followed by high praise or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character named Gemma

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

    No Comments

    Negative Logits
    lihood
    -0.76
    etheless
    -0.76
    erness
    -0.62
    66666666
    -0.62
    skirts
    -0.61
     Pace
    -0.60
     Carly
    -0.59
     opposing
    -0.59
     occasion
    -0.57
     alternate
    -0.57
    POSITIVE LOGITS
    stones
    1.35
    stone
    1.18
    gem
    0.90
    atsu
    0.90
     gems
    0.84
     Gem
    0.81
    ãĥ£
    0.80
    cit
    0.80
    gob
    0.79
    abyte
    0.78
    Activations Density 0.013%

    No Known Activations