© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15591
    Prev
    Next
    INDEX
    Explanations

    references to the state of North Carolina

    oai_token-act-pair · gpt-3.5-turbo

    references to North Carolina

    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
    sch
    -0.79
    uably
    -0.79
    MAT
    -0.74
    shake
    -0.73
    ellery
    -0.72
    NUM
    -0.71
    mat
    -0.71
    housing
    -0.70
    matically
    -0.70
    journal
    -0.69
    POSITIVE LOGITS
    olina
    0.97
     Courage
    0.93
     Carolina
    0.92
     State
    0.90
     Hurricanes
    0.90
     Herrera
    0.81
    urses
    0.81
    sylvania
    0.78
    essee
    0.76
     Edison
    0.75
    Activations Density 0.011%

    No Known Activations