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. 3-RES-JB
    6. 19380
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in specific incidents

    oai_token-act-pair · gpt-3.5-turbo

    specific names of people and related incidents involving them

    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
     pse
    -0.87
    olkien
    -0.84
     shaping
    -0.84
     hitherto
    -0.80
     Kyoto
    -0.79
     Babel
    -0.78
     translated
    -0.78
     Nietzsche
    -0.78
     Sanskrit
    -0.78
     geopolitical
    -0.77
    POSITIVE LOGITS
     County
    0.91
    ville
    0.91
     Police
    0.91
     Correctional
    0.91
     misdemeanor
    0.88
     felony
    0.85
     RCMP
    0.84
     assailant
    0.84
    law
    0.84
     defendants
    0.84
    Activations Density 0.763%

    No Known Activations