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. 22132
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical activities or sports

    oai_token-act-pair · gpt-3.5-turbo

    activities related to sports and physical fitness

    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
     Frey
    -0.70
    ãĥķãĤ©
    -0.69
    xus
    -0.68
    enta
    -0.66
    ãĥ´
    -0.66
    variable
    -0.65
    isy
    -0.64
    ãĤ·ãĥ£
    -0.64
     Glas
    -0.63
    romeda
    -0.61
    POSITIVE LOGITS
     prowess
    0.96
     adventures
    0.94
     skills
    0.90
     enthusiast
    0.90
     etiquette
    0.88
     enthusiasts
    0.88
     fraternity
    0.84
    HAM
    0.81
     sessions
    0.80
     techniques
    0.80
    Activations Density 0.155%

    No Known Activations