© 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. 8-RES-JB
    11. 24513
    Prev
    Next
    INDEX
    Explanations

    phrases related to assessments or considerations of different factors and situations

    oai_token-act-pair · gpt-3.5-turbo

    references to important facts or contexts in discussions

    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
    hent
    -0.80
    MAR
    -0.79
    esar
    -0.73
    HR
    -0.72
    ere
    -0.71
    Minor
    -0.71
    IRT
    -0.69
    fits
    -0.68
    jer
    -0.68
    inis
    -0.67
    POSITIVE LOGITS
     circumstances
    1.29
     context
    1.02
     uncertainties
    0.96
     propensity
    0.95
     circumstance
    0.94
     constraints
    0.94
     proximity
    0.91
     seriousness
    0.90
     nature
    0.90
     pressures
    0.89
    Activations Density 0.096%

    No Known Activations