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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 10506
    Prev
    Next
    INDEX
    Explanations

    words related to types of hops used in brewing

    oai_token-act-pair · gpt-3.5-turbo

    references to hops in the context of brewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Book
    -0.72
     purse
    -0.71
    fit
    -0.67
     Liber
    -0.67
    eless
    -0.66
    eur
    -0.65
    Wall
    -0.65
    inner
    -0.65
     Universal
    -0.64
    ovie
    -0.64
    POSITIVE LOGITS
     hops
    3.97
    hops
    2.17
     peppers
    1.47
     grapes
    1.22
     hopping
    1.21
     squats
    1.16
     hopped
    1.16
     oats
    1.09
     bounces
    1.08
     chops
    1.07
    Activations Density 0.036%

    No Known Activations