© 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. 11-RES-JB
    11. 7501
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "-sensory"

    oai_token-act-pair · gpt-3.5-turbo

    words related to sensory experiences and sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.78
     mant
    -0.63
     Primordial
    -0.58
     Soda
    -0.58
     Takeru
    -0.58
     Dice
    -0.57
     Bezos
    -0.57
     Sovereign
    -0.56
     Virgin
    -0.56
     desks
    -0.56
    POSITIVE LOGITS
    urable
    1.13
    orship
    1.12
    ures
    1.04
    ors
    1.00
    itized
    1.00
    haw
    0.99
    ource
    0.99
    ure
    0.97
    ured
    0.95
    itivity
    0.93
    Activations Density 0.063%

    No Known Activations