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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 21320
    Prev
    Next
    INDEX
    Explanations

    words related to opposition, resistance, and protest

    oai_token-act-pair · gpt-3.5-turbo

    references to protests and opposition to social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceae
    -0.76
     Correspond
    -0.73
     fry
    -0.68
    case
    -0.66
    staking
    -0.63
    eye
    -0.62
     inval
    -0.60
     Tiff
    -0.59
    cases
    -0.59
     glands
    -0.58
    POSITIVE LOGITS
     encro
    0.99
     policies
    0.96
     restrictions
    0.92
     injust
    0.91
     oppression
    0.87
    nesty
    0.87
     legalization
    0.87
    usterity
    0.87
     advances
    0.85
     tyranny
    0.85
    Activations Density 0.530%

    No Known Activations