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. 8168
    Prev
    Next
    INDEX
    Explanations

    words containing the sequence "ou"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "you."

    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
     Capitol
    -0.66
     Shutterstock
    -0.65
    Ö¼
    -0.65
    ãĥķãĤ©
    -0.64
     sanctuary
    -0.64
    è£ħ
    -0.63
    æŃ¦
    -0.62
    èĢħ
    -0.62
     moderators
    -0.60
    aceutical
    -0.59
    POSITIVE LOGITS
    rier
    1.05
    seless
    0.96
    plet
    0.90
    ewater
    0.89
    pling
    0.89
    rown
    0.88
    ven
    0.85
    ctions
    0.83
    riers
    0.82
    pees
    0.81
    Activations Density 0.013%

    No Known Activations