© 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. 2-RES-JB
    11. 12675
    Prev
    Next
    INDEX
    Explanations

    names or words related to "Dum", "Drum", or similar phonetic patterns

    oai_token-act-pair · gpt-3.5-turbo

    the names of people, particularly those related to basketball

    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
    ships
    -0.88
    hips
    -0.82
    leeve
    -0.75
    ģĸ
    -0.72
    ship
    -0.71
    shapeshifter
    -0.71
     AAP
    -0.70
    OHN
    -0.70
     Subtle
    -0.68
    Vector
    -0.68
    POSITIVE LOGITS
     Dum
    1.44
    pty
    1.17
    plings
    1.05
    ont
    1.00
    uz
    0.99
    ming
    0.98
    pling
    0.96
    plin
    0.96
    mer
    0.94
    mers
    0.92
    Activations Density 0.005%

    No Known Activations