© 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. 17458
    Prev
    Next
    INDEX
    Explanations

    terms related to mills

    oai_token-act-pair · gpt-3.5-turbo

    references to "millennials" and related concepts

    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
    lde
    -0.81
     tang
    -0.65
     tailored
    -0.65
     tailor
    -0.64
     pool
    -0.63
     fitting
    -0.63
    worldly
    -0.63
     screened
    -0.62
     yours
    -0.61
    cephal
    -0.60
    POSITIVE LOGITS
    enium
    1.28
    ennial
    1.15
    enn
    1.10
    imet
    1.08
    isec
    1.05
    oton
    1.04
    mill
    0.97
    inois
    0.92
    imeter
    0.92
    arious
    0.91
    Activations Density 0.008%

    No Known Activations