© 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. 0-RES-JB
    11. 8169
    Prev
    Next
    INDEX
    Explanations

    references to colors, particularly shades of brown

    oai_token-act-pair · gpt-3.5-turbo

    references to the color brown

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hw
    -0.73
    eva
    -0.73
    HF
    -0.70
     Wage
    -0.66
    DCS
    -0.66
    hack
    -0.64
     Tracks
    -0.64
    Dest
    -0.64
    Xi
    -0.64
    href
    -0.64
    POSITIVE LOGITS
     brown
    3.48
    brown
    2.89
    Brown
    2.00
     Brown
    1.94
     gray
    1.76
     yellow
    1.76
     grey
    1.71
     green
    1.65
     pink
    1.58
     black
    1.56
    Activations Density 0.015%

    No Known Activations