© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3195
    Prev
    Next
    INDEX
    Explanations

    descriptions related to sensory attributes like taste, color, and texture

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to food and flavor characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ethics
    -0.68
     Loans
    -0.66
     managers
    -0.63
     bargaining
    -0.63
     Surveillance
    -0.62
    ISA
    -0.62
     exploit
    -0.62
     occupation
    -0.60
     expulsion
    -0.60
     taxation
    -0.59
    POSITIVE LOGITS
    ishy
    1.04
    htaking
    1.01
    oreal
    1.00
    zy
    1.00
    ppy
    1.00
    oky
    0.99
    inous
    0.98
    assy
    0.98
    umpy
    0.97
    thereal
    0.97
    Activations Density 0.280%

    No Known Activations