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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13436
    Prev
    Next
    INDEX
    Explanations

    terms related to political resistance

    oai_token-act-pair · gpt-3.5-turbo

    references to resistance movements and actions against oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghazi
    -0.83
    tein
    -0.79
    ewater
    -0.72
    gow
    -0.68
     Loaded
    -0.68
    utra
    -0.67
     Lumpur
    -0.67
     Pengu
    -0.66
    orah
    -0.66
    oba
    -0.65
    POSITIVE LOGITS
     resistance
    0.95
     fighters
    0.78
    istance
    0.75
     Resistance
    0.73
     thereto
    0.73
     regimes
    0.71
    yip
    0.70
    atility
    0.70
     dictate
    0.70
    bands
    0.68
    Activations Density 0.010%

    No Known Activations