© 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 EvalsExportsinterp-engineNEWAPI 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. 4-RES-JB
    11. 1068
    Prev
    Next
    INDEX
    Explanations

    words related to biological membranes and their characteristics, such as pores and permeability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to membranes and their structures

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

    No Comments

    Negative Logits
     Unch
    -0.79
    swick
    -0.78
     WARN
    -0.72
    GM
    -0.72
    KNOWN
    -0.71
    ĸ
    -0.68
     Schwarzenegger
    -0.67
     Hunts
    -0.66
    ICAN
    -0.66
    heimer
    -0.66
    POSITIVE LOGITS
     membrane
    1.15
     membranes
    1.11
    cules
    0.95
    llular
    0.93
     pores
    0.83
     slime
    0.81
     absorbs
    0.80
     perme
    0.80
     muc
    0.80
    cloth
    0.80
    Activations Density 0.015%

    No Known Activations