© 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. 8064
    Prev
    Next
    INDEX
    Explanations

    mentions of specific positions or titles within organizations or communities

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to essential components of education and emotional development

    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
    results
    -0.72
    enges
    -0.67
    oops
    -0.67
    chers
    -0.63
    cdn
    -0.62
    omever
    -0.62
    Results
    -0.62
    ||||
    -0.62
    aways
    -0.61
    edin
    -0.61
    POSITIVE LOGITS
     slang
    0.99
     decentralized
    0.85
     playable
    0.83
     noun
    0.81
     fallacy
    0.81
     abbre
    0.81
     theorem
    0.79
     adjective
    0.77
     verb
    0.77
     multiplayer
    0.77
    Activations Density 0.369%

    No Known Activations