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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16522
    Prev
    Next
    INDEX
    Explanations

    ingredients or objects related to cooking that are brown in color

    oai_token-act-pair · gpt-3.5-turbo

    references to the color brown or related characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.70
    ngth
    -0.68
    amaru
    -0.67
    USS
    -0.65
    udeau
    -0.65
    apist
    -0.63
     Tactics
    -0.61
     Proposition
    -0.61
    cept
    -0.60
    ghai
    -0.59
    POSITIVE LOGITS
    ies
    1.02
    ish
    1.00
    ie
    0.94
    beard
    0.89
    efined
    0.88
    bread
    0.84
     rice
    0.82
     colored
    0.81
    ishes
    0.81
    shirts
    0.80
    Activations Density 0.029%

    No Known Activations