© 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. 9-RES-JB
    11. 15464
    Prev
    Next
    INDEX
    Explanations

    surface-related terms or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to "surface" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enne
    -0.84
    eros
    -0.83
    rams
    -0.81
    orn
    -0.73
    avering
    -0.73
    orns
    -0.71
    umar
    -0.71
    anders
    -0.70
    endo
    -0.70
    naire
    -0.70
    POSITIVE LOGITS
    FACE
    0.84
    tenance
    0.81
    facing
    0.81
     layer
    0.79
     combatants
    0.77
     mount
    0.76
     coating
    0.75
     area
    0.72
     waters
    0.70
     surface
    0.70
    Activations Density 0.046%

    No Known Activations