© 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. 10-RES-JB
    11. 21550
    Prev
    Next
    INDEX
    Explanations

    countries, states, or cities with superlatives or records

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements that indicate the highest or best status of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iter
    -0.70
    earch
    -0.67
    arry
    -0.67
    uate
    -0.66
    yond
    -0.66
    ocument
    -0.65
    untu
    -0.63
    lass
    -0.63
    abee
    -0.62
    essment
    -0.61
    POSITIVE LOGITS
     utmost
    1.17
     widest
    1.13
     highest
    1.13
     capability
    1.07
     lowest
    1.07
     largest
    1.05
     advantage
    1.04
     misfortune
    1.02
     opportunity
    1.02
     distinction
    1.01
    Activations Density 0.076%

    No Known Activations