© 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. 3-RES-JB
    11. 15773
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or official documents

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various objects, concepts, and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĵĺ
    -0.65
    Native
    -0.65
    photos
    -0.64
    î
    -0.64
    ``
    -0.63
     ..."
    -0.60
    âĢ¢âĢ¢
    -0.59
     Bonds
    -0.59
     ..........
    -0.58
    Enlarge
    -0.58
    POSITIVE LOGITS
    ultimate
    0.85
     pane
    0.74
     succeeded
    0.73
     underwent
    0.70
     portion
    0.68
     mechanic
    0.68
     consisted
    0.68
     patched
    0.67
     motto
    0.66
     fared
    0.65
    Activations Density 0.840%

    No Known Activations