© 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. 1-RES-JB
    11. 3513
    Prev
    Next
    INDEX
    Explanations

    words related to a downward movement or a decrease in a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of descent and empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thumbnails
    -0.74
    enegger
    -0.72
     Balanced
    -0.71
    ICAL
    -0.69
    ODUCT
    -0.69
     Pengu
    -0.67
    HEAD
    -0.65
    ALD
    -0.65
    ãĥĥãĥī
    -0.64
    sonian
    -0.64
    POSITIVE LOGITS
     lapse
    0.97
     descent
    0.93
     ende
    0.87
    cember
    0.86
     destro
    0.85
    jection
    0.84
    anship
    0.83
     clearance
    0.83
    uberty
    0.79
    orship
    0.78
    Activations Density 0.030%

    No Known Activations