© 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. 4-RES-JB
    11. 710
    Prev
    Next
    INDEX
    Explanations

    phrases related to fabrication or falsification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to falsification and misrepresentation

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

    No Comments

    Negative Logits
     Empires
    -0.68
     Kingdoms
    -0.67
     Alz
    -0.67
     Apostles
    -0.66
     Surv
    -0.66
     Brilliant
    -0.65
    SPA
    -0.64
     Revenue
    -0.64
    gamer
    -0.63
    IRO
    -0.62
    POSITIVE LOGITS
    ifiers
    1.19
    ified
    1.18
    ifying
    1.14
    eness
    1.11
    ifier
    1.10
    ifiable
    1.09
    esty
    1.05
     fals
    1.05
    itives
    1.04
    ifies
    1.04
    Activations Density 0.011%

    No Known Activations