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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    6. 24512
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to food, structures, and various aspects of industries or systems, particularly in relation to quality, design, and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to food and cooking techniques

    oai_token-act-pair · gpt-3.5-turbo
    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
     Canaver
    -0.68
     Originally
    -0.66
     Beware
    -0.63
     Poster
    -0.62
     Baal
    -0.61
     Uriel
    -0.61
    anwhile
    -0.60
    CHAT
    -0.60
     Charity
    -0.58
     Rue
    -0.57
    POSITIVE LOGITS
     imaginable
    0.72
     configurations
    0.71
    isations
    0.68
     counterparts
    0.65
    iations
    0.65
     fodder
    0.63
    ocations
    0.63
    izations
    0.63
    catentry
    0.62
    otypes
    0.61
    Activations Density 0.855%

    No Known Activations