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. 3-RES-JB
    6. 11888
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement agencies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "CI" or its variations, indicating a focus on certain entities or key terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburg
    -0.89
    wagen
    -0.88
    andowski
    -0.78
    spr
    -0.77
    nesota
    -0.76
    Reviewer
    -0.75
    side
    -0.75
    theless
    -0.75
    sch
    -0.75
    alph
    -0.74
    POSITIVE LOGITS
    CI
    0.95
    ourage
    0.88
    UTION
    0.87
     CI
    0.83
    ANCE
    0.81
     competence
    0.79
    CE
    0.76
    KE
    0.74
    CCC
    0.73
    ANE
    0.72
    Activations Density 0.008%

    No Known Activations