© 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. 532
    Prev
    Next
    INDEX
    Explanations

    specific text related to software commands and configurations

    oai_token-act-pair · gpt-3.5-turbo

    instances of page numbers and related formatting

    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
    ctor
    -0.72
    thus
    -0.71
    cul
    -0.71
     Leilan
    -0.71
    noon
    -0.70
    fty
    -0.66
     Construct
    -0.64
     Chand
    -0.64
    hold
    -0.63
     Arn
    -0.63
    POSITIVE LOGITS
    sql
    1.16
    Pg
    1.06
    pg
    0.95
    asus
    0.90
    ills
    0.88
    ression
    0.83
    maxwell
    0.74
    allery
    0.73
    =#
    0.73
    uments
    0.72
    Activations Density 0.009%

    No Known Activations