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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6-RES-JB
    6. 13915
    Prev
    Next
    INDEX
    Explanations

    words related to physical strength and power

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Buff 2"

    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
    ________________________
    -0.71
     Stras
    -0.71
    FTWARE
    -0.67
     Reign
    -0.62
     Labyrinth
    -0.62
     cloves
    -0.59
    worldly
    -0.59
     Herrera
    -0.58
     domestically
    -0.58
     Worlds
    -0.58
    POSITIVE LOGITS
    alon
    1.13
    ered
    1.10
    alos
    1.06
    oon
    0.97
    aroo
    0.95
    alo
    0.94
    ering
    0.92
    ett
    0.92
    oons
    0.90
    ington
    0.90
    Activations Density 0.020%

    No Known Activations