© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5091
    Prev
    Next
    INDEX
    Explanations

    explicit mentions of the word "false"

    oai_token-act-pair · gpt-3.5-turbo

    references to falsehoods or misleading claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hens
    -1.00
     guiActiveUnfocused
    -0.97
    hetti
    -0.81
    asio
    -0.77
    ajo
    -0.76
    arya
    -0.75
    mun
    -0.75
    rike
    -0.73
    forces
    -0.72
    aldo
    -0.71
    POSITIVE LOGITS
     positives
    1.01
     accuser
    0.89
     guiActiveUn
    0.86
     dich
    0.85
     guiIcon
    0.79
     false
    0.76
     negatives
    0.76
     falsely
    0.76
     accusation
    0.74
     imprisonment
    0.74
    Activations Density 0.019%

    No Known Activations