© 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. 7-RES-JB
    11. 23840
    Prev
    Next
    INDEX
    Explanations

    hyphenated words containing the prefix 'de-' and a subsequent word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to decentralization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LW
    -0.88
     Flavoring
    -0.73
     Baird
    -0.71
     Boxing
    -0.70
     Blacks
    -0.68
     Nurse
    -0.67
     Extras
    -0.67
     Dickinson
    -0.66
     Cassidy
    -0.65
    ODY
    -0.65
    POSITIVE LOGITS
    emphasis
    1.08
    escal
    1.04
    fact
    1.00
    reg
    0.97
    radical
    0.96
    su
    0.91
    de
    0.90
    govern
    0.90
    administ
    0.89
    interest
    0.89
    Activations Density 0.046%

    No Known Activations