© 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 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. 8-RES-JB
    11. 19348
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "The truth is"

    oai_token-act-pair · gpt-3.5-turbo

    statements or assertions that express a fact or truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    throp
    -0.85
    iates
    -0.72
     Improvement
    -0.63
    icipated
    -0.62
    viol
    -0.61
    stad
    -0.61
     derog
    -0.61
    ypes
    -0.60
    ivil
    -0.59
     violation
    -0.58
    POSITIVE LOGITS
     borne
    0.78
     neither
    0.77
     not
    0.74
     probably
    0.73
     unclear
    0.72
     none
    0.71
     indeed
    0.70
     undoubtedly
    0.68
     still
    0.67
     doubtless
    0.67
    Activations Density 0.101%

    No Known Activations