© 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. 9728
    Prev
    Next
    INDEX
    Explanations

    the word "host" and phrases related to a variety of topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a variety of options, instances, or examples

    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
    agate
    -0.73
    ulus
    -0.67
     Walls
    -0.64
     Tycoon
    -0.63
    ensis
    -0.63
    mie
    -0.63
     Dragonbound
    -0.63
    ylan
    -0.63
    istan
    -0.61
    abad
    -0.61
    POSITIVE LOGITS
    otom
    0.71
    dozen
    0.68
    ographical
    0.67
     disparate
    0.67
     dozen
    0.65
     different
    0.65
     ranging
    0.65
     unspecified
    0.65
    different
    0.64
     notable
    0.64
    Activations Density 0.095%

    No Known Activations