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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 14385
    Prev
    Next
    INDEX
    Explanations

    references to global political and economic entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States and its geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.71
     wounding
    -0.68
    thia
    -0.67
     Beir
    -0.66
    groups
    -0.66
    msg
    -0.66
    Cmd
    -0.65
     remem
    -0.63
     incendiary
    -0.63
    itbart
    -0.63
    POSITIVE LOGITS
     consumers
    0.90
     consumer
    0.86
     GDP
    0.85
     Telecom
    0.84
     economies
    0.83
     Investment
    0.82
     Consumer
    0.82
     Dollar
    0.80
     markets
    0.79
     market
    0.79
    Activations Density 0.340%

    No Known Activations