© 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. 1-RES-JB
    11. 14411
    Prev
    Next
    INDEX
    Explanations

    the word "panda" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to pandas, both in terms of the animal and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LOD
    -0.77
    tes
    -0.71
    kick
    -0.70
    phabet
    -0.70
     Skydragon
    -0.69
    IFE
    -0.66
    UV
    -0.65
     Lauder
    -0.65
    dash
    -0.65
    scrib
    -0.65
    POSITIVE LOGITS
     pand
    1.58
    emic
    1.11
    emonium
    1.07
     Pengu
    0.93
     Pand
    0.87
    atown
    0.85
     influenza
    0.82
    Pand
    0.81
    algia
    0.78
    ĸļ
    0.78
    Activations Density 0.005%

    No Known Activations