© 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. 9-RES-JB
    11. 162
    Prev
    Next
    INDEX
    Explanations

    words related to financial activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Fin" followed by the number 2

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.70
     announcer
    -0.67
     Clicker
    -0.65
     clipboard
    -0.62
     employers
    -0.61
    theless
    -0.61
     Lazarus
    -0.60
    Newsletter
    -0.60
     orally
    -0.59
     meanings
    -0.59
    POSITIVE LOGITS
    isher
    1.29
    ishers
    1.25
    anced
    1.16
    ancing
    1.13
    ishing
    1.13
    ishes
    1.05
    itures
    1.02
    ned
    1.02
    anz
    1.01
    ances
    1.00
    Activations Density 0.050%

    No Known Activations