© 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. 6-RES-JB
    11. 17390
    Prev
    Next
    INDEX
    Explanations

    words related to wetness or damp conditions

    oai_token-act-pair · gpt-3.5-turbo

    emotions and states related to fear and moisture

    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
     Scotia
    -0.84
    Downloadha
    -0.76
    ctica
    -0.64
     VIDEOS
    -0.61
     exceptions
    -0.60
     subsistence
    -0.60
     Pompe
    -0.59
     guiActiveUn
    -0.58
     Thumbnails
    -0.58
     Upper
    -0.58
    POSITIVE LOGITS
    ened
    1.93
    ening
    1.72
    eners
    1.57
    ener
    1.27
    ens
    1.16
    en
    1.11
    eter
    1.01
    ems
    0.97
    ded
    0.92
    lied
    0.92
    Activations Density 0.059%

    No Known Activations