Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20269
    Prev
    Next
    INDEX
    Explanations

    words related to barriers or boundaries, specifically the term "fence."

    oai_token-act-pair · gpt-3.5-turbo

    references to barriers, specifically fences and walls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leary
    -0.74
    RESULTS
    -0.72
    NOW
    -0.70
    ucket
    -0.69
    akia
    -0.68
    ":"/
    -0.66
    ived
    -0.65
    Lear
    -0.63
     Lear
    -0.62
     Competitive
    -0.61
    POSITIVE LOGITS
     erected
    1.35
     separating
    1.32
     fence
    1.25
     fences
    1.16
     fencing
    1.15
     perimeter
    1.13
     preventing
    1.10
     barrier
    1.09
     dividing
    1.09
     protecting
    1.08
    Activations Density 0.171%

    No Known Activations