© 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. 3-RES-JB
    11. 1875
    Prev
    Next
    INDEX
    Explanations

    mentions of specific beaches

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Beach."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ativity
    -0.78
    DIT
    -0.73
    urgy
    -0.72
    IUM
    -0.70
    utherford
    -0.70
    demand
    -0.70
    ilyn
    -0.67
    encing
    -0.67
    arial
    -0.65
    selves
    -0.65
    POSITIVE LOGITS
     Beach
    1.09
     Resort
    0.98
     Splash
    0.92
     Boulevard
    0.89
     Island
    0.88
     Gardens
    0.87
    goers
    0.83
     Springs
    0.81
     Blvd
    0.81
     Spit
    0.79
    Activations Density 0.007%

    No Known Activations