© 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. 11-RES-JB
    11. 4239
    Prev
    Next
    INDEX
    Explanations

    words related to specific concepts or technical terms that are mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to fairness and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bie
    -0.51
     Willie
    -0.51
    ogie
    -0.51
    unci
    -0.50
    ke
    -0.50
    ten
    -0.48
     Shak
    -0.47
     Norris
    -0.46
     Maver
    -0.46
    mers
    -0.45
    POSITIVE LOGITS
     fallacy
    0.72
     :=
    0.71
     (%)
    0.68
     =
    0.66
     coefficient
    0.66
     +=
    0.65
    DragonMagazine
    0.64
     calculator
    0.64
    ="
    0.62
     theorem
    0.60
    Activations Density 0.393%

    No Known Activations