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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 8174
    Prev
    Next
    INDEX
    Explanations

    food ingredients, particularly beans and various vegetables like onions, peppers, and almonds

    oai_token-act-pair · gpt-3.5-turbo

    references to beans and related food ingredients

    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
     maneuvers
    -0.77
    minist
    -0.70
    ctor
    -0.67
    pmwiki
    -0.66
    Student
    -0.64
    Witness
    -0.64
     practition
    -0.60
    crime
    -0.60
     circumstance
    -0.59
     defect
    -0.59
    POSITIVE LOGITS
    kins
    1.19
    ynthesis
    1.12
    pring
    1.08
    heet
    1.06
    hips
    1.04
    aurus
    1.02
    poons
    0.99
    creen
    0.97
    cale
    0.96
    mith
    0.96
    Activations Density 0.096%

    No Known Activations