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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4369
    Prev
    Next
    INDEX
    Explanations

    terms related to investments and financial institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investment and financial entities

    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
    unin
    -0.82
    ardless
    -0.81
    ighty
    -0.81
    olson
    -0.80
    izabeth
    -0.77
    unts
    -0.74
    itably
    -0.74
    ocobo
    -0.72
    pron
    -0.71
    ĻĤ
    -0.71
    POSITIVE LOGITS
     Solutions
    1.23
     Fund
    1.16
     Guys
    1.15
     Promotion
    1.12
     Development
    1.12
     Matters
    1.11
     Partnership
    1.10
     Design
    1.09
     Partners
    1.09
     Casting
    1.08
    Activations Density 0.119%

    No Known Activations