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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 12933
    Prev
    Next
    INDEX
    Explanations

    interactions between individuals with titles and formal language, suggesting a conversational setting

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases that include names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igen
    -0.86
    cases
    -0.69
     fueling
    -0.67
     interchange
    -0.67
    edition
    -0.62
    projects
    -0.62
     polar
    -0.62
     seals
    -0.62
     exchanges
    -0.60
     suites
    -0.60
    POSITIVE LOGITS
     Gentleman
    0.85
     Disciple
    0.82
     Beware
    0.81
     beware
    0.78
     thank
    0.77
     congratulations
    0.76
     Dear
    0.73
     please
    0.72
     Metatron
    0.72
     Mistress
    0.72
    Activations Density 0.248%

    No Known Activations