© 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. 13384
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases likely related to specific industries or domains, possibly finance or manufacturing

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to various professional fields and services

    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
    sic
    -0.60
     toget
    -0.57
    代
    -0.57
    ngth
    -0.56
    theless
    -0.56
    ardless
    -0.54
     gren
    -0.53
     destro
    -0.52
    milo
    -0.52
    olson
    -0.51
    POSITIVE LOGITS
     Collection
    0.77
     Simulator
    0.77
     Initiative
    0.74
     Products
    0.73
     Reviews
    0.70
     Rankings
    0.69
     Calculator
    0.69
     Characters
    0.69
     Disorder
    0.69
     Ratings
    0.69
    Activations Density 0.775%

    No Known Activations