© 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. 20244
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically those starting with the letters "Calvin" or "Dominic"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Calvin" as well as references to other prominent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    htar
    -0.99
    yip
    -0.87
    orget
    -0.83
    yll
    -0.82
    roxy
    -0.77
    front
    -0.76
    igation
    -0.76
    eor
    -0.75
    ppa
    -0.75
    rise
    -0.75
    POSITIVE LOGITS
     diapers
    0.82
    ATURES
    0.79
    ATURE
    0.77
    ature
    0.76
    abulary
    0.70
    ibles
    0.70
    adoes
    0.68
     diaper
    0.65
     Bacon
    0.65
    Cub
    0.65
    Activations Density 0.044%

    No Known Activations