© 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. 1246
    Prev
    Next
    INDEX
    Explanations

    mentions of data skewing or being skewed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data representation and distortion

    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
    perial
    -0.65
    founded
    -0.64
    agonist
    -0.64
     Mub
    -0.64
     sweat
    -0.64
     vow
    -0.63
    ossession
    -0.63
     martyr
    -0.62
    monary
    -0.62
     Leban
    -0.62
    POSITIVE LOGITS
     ske
    1.30
     skew
    1.03
     Dise
    0.76
    wn
    0.75
    ws
    0.74
    igible
    0.73
     swings
    0.73
    wered
    0.69
    ^^
    0.69
    lla
    0.68
    Activations Density 0.013%

    No Known Activations