© 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. 2-RES-JB
    11. 21275
    Prev
    Next
    INDEX
    Explanations

    references to luxury automotive brands and models

    oai_token-act-pair · gpt-3.5-turbo

    specific names or terms associated with bicycles and their comparison to luxury automotive brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hodg
    -0.76
     Sinclair
    -0.73
    ALE
    -0.71
    LESS
    -0.64
     DSL
    -0.64
     Rabbit
    -0.63
     Pixie
    -0.62
    agents
    -0.61
    selection
    -0.61
    FACE
    -0.60
    POSITIVE LOGITS
    borgh
    1.60
    illac
    1.07
    ini
    1.04
    inelli
    0.98
    illo
    0.92
    inis
    0.91
    acan
    0.89
    arus
    0.84
    vre
    0.82
    ota
    0.81
    Activations Density 0.012%

    No Known Activations