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. 8-RES-JB
    6. 20606
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or discussing justice

    oai_token-act-pair · gpt-3.5-turbo

    references to justice and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acid
    -0.81
    hetically
    -0.78
    cair
    -0.77
    igslist
    -0.76
    hing
    -0.76
    ramer
    -0.74
    urat
    -0.73
    ergy
    -0.73
    ÃŁ
    -0.69
     Dak
    -0.69
    POSITIVE LOGITS
    fulness
    0.91
    justice
    0.89
    FUL
    0.79
     justice
    0.79
     SYSTEM
    0.76
    lessness
    0.76
     injustice
    0.71
     Gorsuch
    0.70
    cellence
    0.69
    ĪĴ
    0.68
    Activations Density 0.031%

    No Known Activations