© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11612
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Latin America and various countries or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations, organizations, and events

    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
    ordable
    -0.80
    20439
    -0.77
    rador
    -0.77
    ynthesis
    -0.70
    Merit
    -0.67
    bestos
    -0.67
    soever
    -0.66
    posure
    -0.62
    "))
    -0.61
     "$:/
    -0.61
    POSITIVE LOGITS
    pedia
    0.76
     expert
    0.75
     jargon
    0.70
     enthusiast
    0.68
     FAQ
    0.68
     Quarterly
    0.66
    HQ
    0.66
    facts
    0.64
     saga
    0.64
     anecdote
    0.63
    Activations Density 0.908%

    No Known Activations