© 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. 5178
    Prev
    Next
    INDEX
    Explanations

    mentions of time frames such as "the last few years" or "the last few days"

    oai_token-act-pair · gpt-3.5-turbo

    references to recent time periods

    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
     Excellence
    -0.73
    acus
    -0.68
     Auditor
    -0.64
    Report
    -0.62
     thence
    -0.60
     Failure
    -0.60
    atchewan
    -0.59
     Appropri
    -0.59
    UAL
    -0.58
    sal
    -0.57
    POSITIVE LOGITS
     dozen
    1.16
     hundred
    1.15
     weeks
    1.15
     days
    1.11
     months
    1.09
     kilometers
    1.02
     paragraphs
    1.01
     years
    1.00
     thousand
    0.99
    dozen
    0.97
    Activations Density 0.018%

    No Known Activations