© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10053
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial entities, actions, and associated people

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate entities and their activities

    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
     endurance
    -0.81
     fatigue
    -0.80
     stamina
    -0.78
     replay
    -0.78
     applause
    -0.76
     dystopian
    -0.74
     sanity
    -0.74
     instinct
    -0.73
     endings
    -0.72
     adrenaline
    -0.72
    POSITIVE LOGITS
     alias
    1.18
     aliases
    1.08
     subcontract
    1.07
     Manafort
    1.05
    affiliated
    1.04
     lobbyist
    1.02
    registered
    1.02
    aunder
    1.00
     LLC
    1.00
     subsidiaries
    0.99
    Activations Density 0.754%

    No Known Activations