© 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. 5183
    Prev
    Next
    INDEX
    Explanations

    dates and events expressed as numbers in year format

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "to be."

    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
     Lines
    -0.69
     Prescott
    -0.67
     Stain
    -0.65
     sqor
    -0.64
     fray
    -0.60
     residue
    -0.59
     Wick
    -0.58
    anova
    -0.58
     nap
    -0.57
    andra
    -0.57
    POSITIVE LOGITS
    heading
    1.00
     able
    0.99
    fits
    0.98
     judged
    0.96
    leeve
    0.93
    ijing
    0.90
     reckoned
    0.89
    hemoth
    0.88
    ige
    0.88
     seen
    0.87
    Activations Density 0.087%

    No Known Activations