© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24417
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to introducing or introducing a concept/topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "introducing" or variations of it, indicating an introduction or presentation of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.81
     Immunity
    -0.68
     Uniform
    -0.66
     prevailing
    -0.60
    è¦ļéĨĴ
    -0.60
     negatively
    -0.59
    uyomi
    -0.59
    enance
    -0.58
     firsthand
    -0.58
     passwords
    -0.57
    POSITIVE LOGITS
    ctory
    1.66
    ctions
    1.61
    cing
    1.58
    ce
    1.41
    ced
    1.35
    ces
    1.31
    cer
    1.30
    ctive
    1.30
    cé
    1.26
    cible
    1.24
    Activations Density 0.061%

    No Known Activations