© 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. 22621
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of risks in political, social, economic, legal, familial, business, environmental, cognitive, and professional contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of risks and issues within societal structures

    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
    adobe
    -0.74
    enhagen
    -0.72
    abase
    -0.68
    pload
    -0.66
    ModLoader
    -0.66
    eday
    -0.65
    ynthesis
    -0.64
    thens
    -0.64
    acket
    -0.64
    dayName
    -0.63
    POSITIVE LOGITS
     alike
    1.44
     sectors
    1.12
     perspectives
    0.99
     spheres
    0.98
     industries
    0.98
     worlds
    0.96
     fronts
    0.92
     environments
    0.91
     contexts
    0.91
     identities
    0.91
    Activations Density 0.305%

    No Known Activations