© 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. 22173
    Prev
    Next
    INDEX
    Explanations

    words related to different settings and contexts, such as cities, arenas, worlds, and countries

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the balance of power and social structure in various contexts

    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
    soType
    -0.68
    pite
    -0.66
     Tun
    -0.66
     Scotia
    -0.62
    UPDATE
    -0.62
     Hallow
    -0.61
     Hampton
    -0.60
     Indigo
    -0.60
     Receiver
    -0.59
     Recipe
    -0.59
    POSITIVE LOGITS
     dominates
    0.97
     predomin
    0.95
     intersect
    0.94
     flourish
    0.94
     mattered
    0.92
     collide
    0.89
     excel
    0.88
     clashed
    0.86
     dominate
    0.86
     freely
    0.82
    Activations Density 0.460%

    No Known Activations