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. 15651
    Prev
    Next
    INDEX
    Explanations

    phrases related to animals' body parts, particularly 'paw'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific animals or pet-related terminology

    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
     Luther
    -0.78
    idy
    -0.74
    uve
    -0.68
     Protestant
    -0.65
    azel
    -0.65
    ancock
    -0.65
    itud
    -0.64
    illery
    -0.63
    apes
    -0.62
    iblical
    -0.62
    POSITIVE LOGITS
     Paw
    1.22
    bats
    0.92
    ÅĤ
    0.83
    atche
    0.83
    aii
    0.81
    lyak
    0.80
    istani
    0.80
    emonium
    0.79
    asus
    0.76
     paw
    0.75
    Activations Density 0.016%

    No Known Activations