Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22528
    Prev
    Next
    INDEX
    Explanations

    mentions of food preparation techniques involving drying

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drying and dehydrating food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogun
    -0.75
    ority
    -0.74
    adia
    -0.71
    awaru
    -0.69
    ppard
    -0.69
    berman
    -0.69
    erville
    -0.68
    anco
    -0.68
    Developer
    -0.67
    justice
    -0.67
    POSITIVE LOGITS
     apr
    0.75
     Goods
    0.74
    ãģ®éŃĶ
    0.68
    ucing
    0.68
    uces
    0.67
    uce
    0.67
     fruits
    0.66
     drying
    0.65
    ancer
    0.64
    ources
    0.62
    Activations Density 0.029%

    No Known Activations