© 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. 10-RES-JB
    11. 7785
    Prev
    Next
    INDEX
    Explanations

    phrases related to crude oil and related industries

    oai_token-act-pair · gpt-3.5-turbo

    words that start with "Cr" or variations of that prefix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folk
    -0.69
     Brach
    -0.64
     Forever
    -0.64
    manship
    -0.63
    lihood
    -0.63
     Helsinki
    -0.59
     GOODMAN
    -0.59
     Mechdragon
    -0.59
     Wildcats
    -0.59
     Flickr
    -0.59
    POSITIVE LOGITS
    adle
    1.39
    acker
    1.33
    ackers
    1.30
    utch
    1.21
    acked
    1.21
    acking
    1.20
    ude
    1.17
    acks
    1.16
    ushed
    1.16
    addock
    1.15
    Activations Density 0.016%

    No Known Activations