© 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. 0-RES-JB
    11. 8398
    Prev
    Next
    INDEX
    Explanations

    mentions of physical barriers or boundaries, specifically fences

    oai_token-act-pair · gpt-3.5-turbo

    references to fences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aming
    -0.79
    Instant
    -0.78
    uddin
    -0.67
    zin
    -0.63
    uz
    -0.62
     Kathleen
    -0.62
    izz
    -0.61
    ames
    -0.61
    Q
    -0.60
    Eng
    -0.60
    POSITIVE LOGITS
     fence
    3.92
     fences
    2.93
     fencing
    2.10
     wall
    1.34
     barrier
    1.32
     barric
    1.30
     railing
    1.26
     cage
    1.23
     perimeter
    1.19
     gate
    1.15
    Activations Density 0.016%

    No Known Activations