© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 10927
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    references to abundance or variety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quart
    -0.71
    hower
    -0.65
     WARN
    -0.62
     Auth
    -0.61
    witz
    -0.60
    rison
    -0.60
    IGHT
    -0.58
    APTER
    -0.58
    iew
    -0.56
    Leaks
    -0.56
    POSITIVE LOGITS
     assorted
    1.03
    cellaneous
    0.82
    Downloadha
    0.82
     occasional
    0.77
    etc
    0.74
     importantly
    0.72
    whatever
    0.71
    anything
    0.68
     general
    0.67
     downright
    0.67
    Activations Density 0.371%

    No Known Activations