© 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. 1-RES-JB
    11. 9438
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles that may include the word "Col."

    oai_token-act-pair · gpt-3.5-turbo

    references to colors or color-related terminology

    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
    cffff
    -0.99
    wered
    -0.81
    natureconservancy
    -0.73
     forth
    -0.72
    cffffcc
    -0.70
    shapeshifter
    -0.65
     Werewolf
    -0.64
    ARP
    -0.62
    dayName
    -0.61
    ItemTracker
    -0.61
    POSITIVE LOGITS
    Col
    1.03
    onel
    1.02
    onial
    0.98
    ossal
    0.95
    ombo
    0.92
    ossus
    0.91
    lections
    0.87
    ouri
    0.87
    leen
    0.87
    orsche
    0.85
    Activations Density 0.007%

    No Known Activations