© 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. 11-RES-JB
    11. 6896
    Prev
    Next
    INDEX
    Explanations

    information about travel destinations and experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to exploration and discovery in various contexts

    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
     RNC
    -0.82
    ahon
    -0.78
    osterone
    -0.78
    Republican
    -0.77
     Boehner
    -0.77
    ricane
    -0.73
    ariat
    -0.73
     Republican
    -0.73
     Majority
    -0.71
    elfare
    -0.70
    POSITIVE LOGITS
     explorers
    1.56
     curiosity
    1.44
     explorer
    1.41
     exploration
    1.37
     fascinated
    1.34
     discoveries
    1.34
     explor
    1.30
     exploring
    1.30
     adventure
    1.28
     fascination
    1.25
    Activations Density 0.685%

    No Known Activations