© 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. 2-RES-JB
    11. 17332
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific research methods, specifically the technique of simulating gemstones in a petri dish

    oai_token-act-pair · gpt-3.5-turbo

    references to materials used in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.84
    manship
    -0.80
    vity
    -0.76
    leep
    -0.76
    sembly
    -0.74
    erate
    -0.74
    ruciating
    -0.74
    smanship
    -0.73
    open
    -0.73
    sym
    -0.72
    POSITIVE LOGITS
    Appearances
    0.72
     Swan
    0.65
     Shares
    0.65
     Hollow
    0.64
    Born
    0.64
     Revolution
    0.62
     Croat
    0.60
    MSN
    0.60
     Goddess
    0.60
     Stain
    0.59
    Activations Density 0.000%

    No Known Activations