© 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. 1-RES-JB
    11. 3656
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those related to legal or ethical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estern
    -0.79
    DragonMagazine
    -0.76
    rawdownloadcloneembedreportprint
    -0.75
    atoon
    -0.74
    ãĥĺ
    -0.74
     Phantom
    -0.71
     Bei
    -0.70
    ãĥ´ãĤ¡
    -0.69
     Labrador
    -0.69
    é»Ĵ
    -0.68
    POSITIVE LOGITS
     Neh
    0.88
    iry
    0.78
    hemy
    0.75
    wr
    0.72
    terness
    0.68
     âĸº
    0.67
    emic
    0.66
     streak
    0.66
    hani
    0.65
    elin
    0.65
    Activations Density 0.015%

    No Known Activations