© 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. 1-RES-JB
    11. 14300
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Def" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    the term "Def" related to policies or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.75
    akeru
    -0.72
    ocene
    -0.72
    DragonMagazine
    -0.68
    Ħ¢
    -0.67
    Reviewer
    -0.66
    externalActionCode
    -0.65
    worldly
    -0.63
    stery
    -0.62
     Dragonbound
    -0.61
    POSITIVE LOGITS
     Def
    1.02
    initions
    1.00
    aults
    0.91
    icit
    0.90
    ibr
    0.89
    Def
    0.87
    enses
    0.86
    rag
    0.86
    ainer
    0.85
    ensor
    0.85
    Activations Density 0.009%

    No Known Activations