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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 13355
    Prev
    Next
    INDEX
    Explanations

    statements related to political criticism

    oai_token-act-pair · gpt-3.5-turbo

    statements related to political discussions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hawai
    -1.06
     utilized
    -0.94
     utilize
    -0.85
     thru
    -0.84
     utilizes
    -0.83
     utilizing
    -0.80
    á¸
    -0.80
     anyways
    -0.78
    caliber
    -0.76
    entimes
    -0.76
    POSITIVE LOGITS
     Ukip
    1.60
     Labour
    1.47
     UKIP
    1.42
    Labour
    1.41
     Tory
    1.38
     £
    1.36
     Corbyn
    1.33
     Tories
    1.33
     Miliband
    1.32
     SNP
    1.30
    Activations Density 1.401%

    No Known Activations