© 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. 1-RES-JB
    11. 3169
    Prev
    Next
    INDEX
    Explanations

    references to trade deals and agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to trade deals and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noon
    -0.66
     Prairie
    -0.66
    guyen
    -0.64
     Prec
    -0.64
     gall
    -0.61
     Barton
    -0.61
    wild
    -0.60
    mare
    -0.59
     Staten
    -0.59
     Ath
    -0.58
    POSITIVE LOGITS
     deals
    1.30
     horizont
    0.97
     Deals
    0.92
     deal
    0.91
    hips
    0.90
     agreements
    0.87
    deals
    0.85
    deal
    0.85
    ership
    0.82
     negoti
    0.80
    Activations Density 0.008%

    No Known Activations