© 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. 6-RES-JB
    11. 17115
    Prev
    Next
    INDEX
    Explanations

    terms related to digging or excavation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'Dig' or variations of it, often relating to media or marketing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fenrir
    -0.68
     ACTIONS
    -0.68
     Russo
    -0.64
     SAL
    -0.62
    ãģ®éŃĶ
    -0.62
     Severus
    -0.61
    OHN
    -0.60
     spare
    -0.58
     hell
    -0.58
     Perse
    -0.58
    POSITIVE LOGITS
    itized
    1.23
    imon
    1.19
    gers
    1.18
    ibility
    1.17
    ible
    1.07
    ging
    1.03
    raph
    1.02
    ibles
    1.01
    ger
    1.01
    acy
    1.00
    Activations Density 0.022%

    No Known Activations