© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    statements indicating truth or honesty

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of truth

    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
    eds
    -0.73
    anus
    -0.71
    uled
    -0.70
    cca
    -0.70
    hire
    -0.68
    eda
    -0.67
    akuya
    -0.67
    wana
    -0.67
     fever
    -0.67
    oso
    -0.64
    POSITIVE LOGITS
    fulness
    0.97
    UTH
    0.80
    displayText
    0.74
    psons
    0.74
     extent
    0.74
     thereof
    0.70
     Dome
    0.69
    liest
    0.67
     truth
    0.65
     srfAttach
    0.65
    Activations Density 0.055%

    No Known Activations