© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 3018
    Prev
    Next
    INDEX
    Explanations

    mentions of superlatives related to low levels or records

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating the lowest points or rates in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĪ
    -0.68
    ensional
    -0.64
    ernels
    -0.63
    die
    -0.62
    umbn
    -0.61
     Extras
    -0.60
    enegger
    -0.60
    dit
    -0.59
     Bullets
    -0.59
    DragonMagazine
    -0.58
    POSITIVE LOGITS
     EVER
    1.12
     ever
    1.11
    ever
    1.09
     since
    1.00
     recorded
    0.92
    since
    0.85
     consecutive
    0.80
     Gallup
    0.80
     Recorded
    0.79
     percentage
    0.76
    Activations Density 0.160%

    No Known Activations