Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10497
    Prev
    Next
    INDEX
    Explanations

    food-related words, especially related to feasting and banquets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to feasting and banquets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Negative
    -0.75
     USAF
    -0.73
    lost
    -0.63
    negative
    -0.63
    gemony
    -0.62
    legal
    -0.61
    Merit
    -0.60
     Archangel
    -0.59
    plets
    -0.59
    angel
    -0.58
    POSITIVE LOGITS
     feast
    1.19
     Feast
    1.03
    efully
    0.88
    oleon
    0.85
    ctuary
    0.84
     meals
    0.81
    ãĥ¼ãĥĨãĤ£
    0.80
    icip
    0.79
    Hunt
    0.77
     supper
    0.77
    Activations Density 0.014%

    No Known Activations