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. 4259
    Prev
    Next
    INDEX
    Explanations

    mentions of spa facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to spas and related establishments

    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
     Scotia
    -0.80
     Creed
    -0.72
    selves
    -0.70
    ©¶æ¥µ
    -0.69
    è¦ļéĨĴ
    -0.69
     corrid
    -0.68
     Skies
    -0.67
    gdala
    -0.67
     captcha
    -0.66
    otos
    -0.66
    POSITIVE LOGITS
    enstein
    0.90
    eners
    0.89
    ENS
    0.88
    ener
    0.86
    hes
    0.84
    ensing
    0.81
    lasses
    0.80
    kers
    0.74
    spring
    0.74
    ulously
    0.74
    Activations Density 0.035%

    No Known Activations