© 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. 19085
    Prev
    Next
    INDEX
    Explanations

    mentions of agricultural departments and related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to agricultural organizations and regulations

    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
    gotten
    -0.75
    iations
    -0.73
    onto
    -0.73
     poles
    -0.65
    light
    -0.64
     Cheong
    -0.64
    bies
    -0.64
    angelo
    -0.63
    ople
    -0.62
    iable
    -0.62
    POSITIVE LOGITS
     nutrit
    0.81
    ¶ħ
    0.78
     kosher
    0.78
    Food
    0.76
    ERY
    0.76
     gastro
    0.75
    Meat
    0.74
     Beef
    0.73
    Ļ½
    0.72
     beet
    0.72
    Activations Density 0.068%

    No Known Activations