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. 15837
    Prev
    Next
    INDEX
    Explanations

    mentions of addresses or locations

    oai_token-act-pair · gpt-3.5-turbo

    important structural details and elements of a construction project

    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
    cipl
    -0.88
    20439
    -0.87
    æĹ
    -0.81
    TT
    -0.79
    playing
    -0.77
    γ
    -0.77
    peer
    -0.76
    Downloadha
    -0.76
    æĺ
    -0.76
    TPP
    -0.76
    POSITIVE LOGITS
     renovation
    1.41
     renovations
    1.33
     facility
    1.30
     renovated
    1.29
     redevelopment
    1.27
     demolition
    1.23
     building
    1.22
     facade
    1.16
     plaza
    1.16
     buildings
    1.15
    Activations Density 0.258%

    No Known Activations