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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 3694
    Prev
    Next
    INDEX
    Explanations

    references to billboards and signs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to billboards

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thro
    -0.77
     Continent
    -0.73
    enne
    -0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.69
    ivot
    -0.69
    culus
    -0.69
     Ago
    -0.68
    oglu
    -0.68
    erate
    -0.67
    >[
    -0.67
    POSITIVE LOGITS
     billboards
    1.24
     billboard
    1.23
     erected
    1.06
     signage
    1.00
     advertising
    0.95
     banners
    0.91
    posts
    0.90
     proclaiming
    0.89
    posted
    0.86
     dotted
    0.84
    Activations Density 0.023%

    No Known Activations