© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4893
    Prev
    Next
    INDEX
    Explanations

    mentions of events or entities related to live performances, particularly music concerts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to airline or headline context

    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
    rity
    -0.90
    ortion
    -0.77
    lished
    -0.74
    rek
    -0.72
    anooga
    -0.68
    Owner
    -0.68
    docs
    -0.68
     Seym
    -0.67
    lying
    -0.67
    nee
    -0.66
    POSITIVE LOGITS
    backer
    0.84
    strument
    0.75
    comed
    0.73
    pread
    0.73
    UX
    0.71
    ovie
    0.67
     Hebdo
    0.67
     Rouge
    0.64
    gdala
    0.64
    mith
    0.63
    Activations Density 0.015%

    No Known Activations