© 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. 4-RES-JB
    11. 7203
    Prev
    Next
    INDEX
    Explanations

    words related to dampness and moist conditions

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to moisture and dampness

    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
     VIDEOS
    -0.87
    OPLE
    -0.73
    ioch
    -0.72
    ICO
    -0.67
    ################
    -0.66
     Pipeline
    -0.66
    ICAL
    -0.66
    Downloadha
    -0.66
     Prosecut
    -0.66
     Robb
    -0.63
    POSITIVE LOGITS
    ened
    1.21
    ening
    1.09
    eners
    1.03
    ener
    1.02
    ness
    1.02
     damp
    0.94
    ding
    0.92
    est
    0.86
    stress
    0.85
    resses
    0.81
    Activations Density 0.011%

    No Known Activations