© 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. 7-RES-JB
    11. 3044
    Prev
    Next
    INDEX
    Explanations

    terms related to mass or mass-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mass and gravity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.80
     Sark
    -0.74
     Nights
    -0.68
    BOOK
    -0.67
     Homeless
    -0.65
    ©¶æ
    -0.65
    ¾
    -0.65
    OTA
    -0.64
     Breath
    -0.64
     Violence
    -0.64
    POSITIVE LOGITS
     ratio
    0.87
    lessness
    0.85
     ratios
    0.82
    atsu
    0.79
    eter
    0.78
    houses
    0.78
    achusetts
    0.76
    ribution
    0.75
     quantities
    0.74
    riction
    0.74
    Activations Density 0.045%

    No Known Activations