© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4574
    Prev
    Next
    INDEX
    Explanations

    common words related to physical structures, specifically walls

    oai_token-act-pair · gpt-3.5-turbo

    references to physical walls or barriers in various contexts

    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
    Gene
    -0.70
    Published
    -0.67
    INA
    -0.66
    ATIONAL
    -0.65
    ya
    -0.65
    itarian
    -0.62
    forward
    -0.62
    sb
    -0.62
    phrine
    -0.61
    Medic
    -0.61
    POSITIVE LOGITS
     walls
    1.23
    papers
    0.98
    abies
    0.94
     Walls
    0.90
    aby
    0.89
     wall
    0.89
    mith
    0.81
     wallpaper
    0.80
    paper
    0.78
    eries
    0.76
    Activations Density 0.013%

    No Known Activations