© 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
    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. 153
    Prev
    Next
    INDEX
    Explanations

    financial terms related to gains or advantages

    oai_token-act-pair · gpt-3.5-turbo

    references to advantages or positive outcomes

    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
    lio
    -0.66
    vez
    -0.65
     Monstrous
    -0.62
    ua
    -0.62
     Puzzles
    -0.62
    parts
    -0.62
     Penal
    -0.61
    gently
    -0.61
     Hole
    -0.61
    ger
    -0.61
    POSITIVE LOGITS
     conferred
    1.21
     outwe
    1.04
     accrued
    1.02
    ocratic
    1.00
     outweigh
    0.96
     claimants
    0.90
    iciary
    0.85
    itism
    0.85
    ocracy
    0.84
     bestowed
    0.83
    Activations Density 0.048%

    No Known Activations