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. 12-RES-JB
    6. 15068
    Prev
    Next
    INDEX
    Explanations

    pet animals, specifically dogs and cats

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to dogs and related pet terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Animals

    No Comments

    Negative Logits
    esson
    -0.84
     Edison
    -0.66
     Sacrament
    -0.66
     Metatron
    -0.64
     EB
    -0.63
     Lank
    -0.62
    unda
    -0.62
    artz
    -0.61
    DERR
    -0.60
     Tesla
    -0.60
    POSITIVE LOGITS
    fighting
    1.17
    fight
    1.17
    matic
    1.14
    matically
    1.11
    gie
    1.08
    fights
    1.08
    shit
    1.06
     barking
    1.05
    tags
    1.02
    fighter
    1.00
    Activations Density 0.064%

    No Known Activations