© 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. 1-RES-JB
    11. 10401
    Prev
    Next
    INDEX
    Explanations

    mentions of sensitivity-related language and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to sensitivity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Camel
    -0.69
     Gall
    -0.67
     Brit
    -0.63
    gone
    -0.62
    thus
    -0.62
     Pillar
    -0.62
    clamation
    -0.62
     Mond
    -0.62
     Springer
    -0.62
    eu
    -0.61
    POSITIVE LOGITS
     sensitivity
    1.51
    ivities
    1.20
     sensit
    1.18
    ensitivity
    1.10
     sensitive
    1.04
    itivity
    0.97
    ensitive
    0.92
     proble
    0.90
    imei
    0.86
     guiActiveUn
    0.83
    Activations Density 0.010%

    No Known Activations