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. 3-RES-JB
    6. 10955
    Prev
    Next
    INDEX
    Explanations

    words related to rabbits

    oai_token-act-pair · gpt-3.5-turbo

    references to rabbits and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igmat
    -0.80
    omething
    -0.77
    ician
    -0.76
    ructure
    -0.71
    rylic
    -0.71
    orship
    -0.69
    rators
    -0.69
    iaries
    -0.69
    raints
    -0.69
     legitimacy
    -0.68
    POSITIVE LOGITS
    MQ
    1.15
     Rabbit
    1.05
     rabbit
    0.95
    fish
    0.92
     Hole
    0.90
    meat
    0.88
     Nest
    0.86
     Hunt
    0.82
     rabbits
    0.82
    Ele
    0.79
    Activations Density 0.008%

    No Known Activations