© 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. 19458
    Prev
    Next
    INDEX
    Explanations

    words related to strength, power, and superiority

    oai_token-act-pair · gpt-3.5-turbo

    references to "super" as a prefix in various contexts

    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
     NEC
    -0.70
     Byrd
    -0.70
     Shepard
    -0.65
    Topics
    -0.65
    ĸļ
    -0.63
    cember
    -0.63
     omission
    -0.62
    PLA
    -0.60
     Lange
    -0.60
     Luxem
    -0.60
    POSITIVE LOGITS
    olester
    0.86
    rencies
    0.85
    roid
    0.82
    itions
    0.79
    anny
    0.78
    uctor
    0.75
    idon
    0.73
    ioxid
    0.73
    anium
    0.73
    illance
    0.72
    Activations Density 0.107%

    No Known Activations