© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 13564
    Prev
    Next
    INDEX
    Explanations

    the word "nuts" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nuts" in various contexts

    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
    pless
    -0.70
    naire
    -0.65
    nered
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
     Cheong
    -0.63
    oping
    -0.63
    Anne
    -0.61
    lon
    -0.61
    âĢ¢âĢ¢
    -0.60
    LESS
    -0.60
    POSITIVE LOGITS
     nuts
    1.24
    ħĭ
    0.96
     peanuts
    0.85
    mith
    0.81
    nuts
    0.81
    terday
    0.78
     nut
    0.78
    hots
    0.75
     bacon
    0.73
    erker
    0.71
    Activations Density 0.008%

    No Known Activations