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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6992
    Prev
    Next
    INDEX
    Explanations

    words related to political actions and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to sanctions or restrictions imposed by authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    incinn
    -0.77
     ********************************
    -0.75
    ********************************
    -0.74
    acea
    -0.73
    mens
    -0.71
     Dems
    -0.70
    #$#$
    -0.69
     Misc
    -0.69
    ________________________________________________________________
    -0.67
     Angle
    -0.67
    POSITIVE LOGITS
     tariffs
    0.94
     compulsory
    0.93
     tougher
    0.90
     airstrikes
    0.87
     preliminary
    0.87
     provisional
    0.87
     fresh
    0.86
     visa
    0.86
     tighter
    0.86
     diplomatic
    0.85
    Activations Density 0.349%

    No Known Activations