© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20986
    Prev
    Next
    INDEX
    Explanations

    financial terms related to funds or investments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of financial stability or funding entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iating
    -0.69
     Verge
    -0.66
     ca
    -0.65
     joking
    -0.62
    ean
    -0.61
     Ved
    -0.61
     Hyundai
    -0.60
     Sheldon
    -0.59
    making
    -0.59
     Arbor
    -0.59
    POSITIVE LOGITS
    FS
    1.18
    ESSION
    1.00
    ystem
    0.99
    DF
    0.91
    ruits
    0.91
    avorite
    0.91
    ometimes
    0.91
     filesystem
    0.90
    Ds
    0.89
    andom
    0.87
    Activations Density 0.011%

    No Known Activations