© 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. 21303
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions and economic contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases and contexts related to financial institutions and their interactions with other entities

    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
     Canaver
    -0.65
    aqu
    -0.65
    inho
    -0.62
    finger
    -0.62
     Constantine
    -0.59
    Ear
    -0.59
    Tel
    -0.58
    ËĪ
    -0.57
     Luffy
    -0.55
    cised
    -0.54
    POSITIVE LOGITS
     respective
    1.12
     system
    1.08
     overall
    1.06
     remainder
    1.05
     entire
    1.05
     broader
    1.03
     rest
    1.01
     institution
    1.01
     organization
    0.98
     entirety
    0.95
    Activations Density 0.442%

    No Known Activations