© 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. 12648
    Prev
    Next
    INDEX
    Explanations

    phrases related to blending or mixing different elements together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blend" and its variations

    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
    selves
    -0.73
     negligent
    -0.66
    dem
    -0.66
    OTO
    -0.66
    IGHTS
    -0.65
     Flyers
    -0.61
    ockets
    -0.61
    useum
    -0.61
    obiles
    -0.60
    taining
    -0.60
    POSITIVE LOGITS
     blends
    1.17
     blend
    1.14
     blending
    1.04
     Flavoring
    0.86
     Blend
    0.80
     seamlessly
    0.80
     blended
    0.80
    atio
    0.74
     mixes
    0.73
    halla
    0.71
    Activations Density 0.008%

    No Known Activations