© 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. 8-RES-JB
    11. 2430
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Ham" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ham" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.71
     Staples
    -0.66
    ç«
    -0.65
     Leone
    -0.63
    igslist
    -0.62
     validity
    -0.60
    vironment
    -0.59
     Buffy
    -0.59
     mushrooms
    -0.59
     Kraken
    -0.58
    POSITIVE LOGITS
    mers
    1.36
    elin
    1.24
    pton
    1.16
    ilton
    1.16
    strings
    1.14
    ster
    1.13
    pering
    1.08
    mer
    1.05
    sterdam
    1.04
    ming
    1.04
    Activations Density 0.016%

    No Known Activations