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. 22604
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gary Ridgway", who is also known as the Green River Killer

    oai_token-act-pair · gpt-3.5-turbo

    the letter "g"

    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
     psychiat
    -0.78
     compr
    -0.74
    ĸļ
    -0.72
     scrut
    -0.69
     mosqu
    -0.68
     concess
    -0.67
    oÄŁ
    -0.66
     certific
    -0.64
     refere
    -0.63
     ridden
    -0.63
    POSITIVE LOGITS
    uild
    1.27
    reens
    1.15
    ossip
    1.12
    raphic
    1.11
    asp
    1.11
    raphics
    1.09
    hetto
    1.06
    rosso
    1.05
    mt
    1.05
    raham
    1.03
    Activations Density 0.037%

    No Known Activations