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. 4-RES-JB
    6. 23569
    Prev
    Next
    INDEX
    Explanations

    references to NATO and OPEC

    oai_token-act-pair · gpt-3.5-turbo

    references to NATO and its activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Jord
    -0.76
    âĸ¬
    -0.73
    sbm
    -0.70
    Wheel
    -0.68
     ancest
    -0.67
    ,,,,,,,,
    -0.67
    ient
    -0.66
    obo
    -0.66
     Hutchinson
    -0.65
     Gron
    -0.65
    POSITIVE LOGITS
     Nato
    1.00
     annex
    0.95
    istani
    0.90
    ilateral
    0.89
     treaty
    0.89
     ally
    0.81
     allies
    0.81
     NATO
    0.80
     cens
    0.78
     superpower
    0.78
    Activations Density 0.007%

    No Known Activations