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. 11-RES-JB
    6. 8490
    Prev
    Next
    INDEX
    Explanations

    references to identification, such as forms of ID and voter identification laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with voter identification requirements and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    storms
    -0.81
    ovie
    -0.79
     pandemonium
    -0.77
    noon
    -0.75
    frey
    -0.75
    optim
    -0.72
    scenes
    -0.71
    twitch
    -0.70
    task
    -0.70
     msec
    -0.70
    POSITIVE LOGITS
     passports
    1.59
     passport
    1.55
     identification
    1.46
     IDs
    1.45
     ID
    1.40
     Identification
    1.31
     fingerprints
    1.25
     credentials
    1.22
     visas
    1.19
     citizenship
    1.16
    Activations Density 0.340%

    No Known Activations