© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1874
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds

    oai_token-act-pair · gpt-3.5-turbo

    references to specific substances or names, particularly related to food or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freak
    -0.70
    iliary
    -0.64
     hereafter
    -0.62
    icipated
    -0.60
    govtrack
    -0.59
    izoph
    -0.59
     greet
    -0.58
     aroma
    -0.56
    roleum
    -0.56
     Sail
    -0.56
    POSITIVE LOGITS
    steen
    1.07
    ornia
    0.76
    ipedia
    0.73
    phia
    0.73
    Avg
    0.73
    esi
    0.71
    ibrary
    0.64
    endi
    0.64
    Ń·
    0.64
    opal
    0.63
    Activations Density 0.295%

    No Known Activations