© 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 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. 6-RES-JB
    11. 23719
    Prev
    Next
    INDEX
    Explanations

    phrases related to ventilation or air movement

    oai_token-act-pair · gpt-3.5-turbo

    references to "vent" or ventilation-related terms

    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
     Hitman
    -0.70
    lean
    -0.69
    FT
    -0.68
    ģĸ
    -0.67
    Else
    -0.66
    makers
    -0.65
    Ĭ±
    -0.64
    HCR
    -0.62
     Witcher
    -0.61
    UTERS
    -0.60
    POSITIVE LOGITS
    ricular
    1.45
    ilated
    1.27
    ral
    1.21
    urous
    1.11
    rue
    1.09
    ilation
    1.07
    uring
    0.97
    uri
    0.96
    illation
    0.91
    iliary
    0.87
    Activations Density 0.018%

    No Known Activations