© 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. 3-RES-JB
    11. 15102
    Prev
    Next
    INDEX
    Explanations

    securities-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "securities" and related regulatory terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liness
    -0.79
    riot
    -0.77
    RM
    -0.73
     Ridley
    -0.72
    frey
    -0.69
    OVA
    -0.68
    ILE
    -0.66
     granite
    -0.66
    lihood
    -0.66
    ľ
    -0.65
    POSITIVE LOGITS
     securities
    1.02
     filings
    1.00
    ratulations
    0.93
     Securities
    0.91
     holdings
    0.90
     portfolio
    0.86
     Exchange
    0.82
    folio
    0.81
    ription
    0.80
     brokerage
    0.78
    Activations Density 0.014%

    No Known Activations