© 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. 2985
    Prev
    Next
    INDEX
    Explanations

    names of people, places, books, and terms related to different topics

    oai_token-act-pair · gpt-3.5-turbo

    titles of specific works (films, books, etc.) and associated keywords

    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
    Downloadha
    -0.76
    etheless
    -0.73
     constitu
    -0.71
    opausal
    -0.68
    otine
    -0.68
    olson
    -0.67
    ãĢı
    -0.67
    ĻĤ
    -0.66
    ounter
    -0.66
    perature
    -0.63
    POSITIVE LOGITS
     Shots
    0.94
     Coverage
    0.94
     Room
    0.93
     Productions
    0.92
     Characters
    0.92
     Score
    0.89
     Points
    0.88
     Matters
    0.88
     Transfer
    0.87
     Rooms
    0.86
    Activations Density 0.652%

    No Known Activations