© 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. 4-RES-JB
    11. 17354
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'dried'

    oai_token-act-pair · gpt-3.5-turbo

    references to dried or dehydrated food items and ingredients

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

    No Comments

    Negative Logits
    awaru
    -0.70
    ogun
    -0.70
    ordan
    -0.69
    leading
    -0.69
    ppard
    -0.69
    ority
    -0.69
    adia
    -0.68
     justices
    -0.67
     headlined
    -0.67
    anchester
    -0.67
    POSITIVE LOGITS
     drying
    0.81
     apr
    0.79
     fruits
    0.71
     Goods
    0.71
     dried
    0.70
    uces
    0.69
    uce
    0.68
     fruit
    0.68
     exting
    0.67
     herbs
    0.67
    Activations Density 0.011%

    No Known Activations