© 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. 9461
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ene"

    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
    frames
    -0.83
    oons
    -0.72
    ties
    -0.71
    istically
    -0.70
    gerald
    -0.70
    talk
    -0.69
    deck
    -0.64
    lime
    -0.64
    DOC
    -0.63
    ifact
    -0.63
    POSITIVE LOGITS
    uve
    1.19
    utics
    1.18
    utical
    1.06
     Wenger
    0.98
    agles
    0.97
    quin
    0.96
    alogy
    0.94
    esis
    0.86
    utic
    0.85
    lements
    0.82
    Activations Density 0.008%

    No Known Activations