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. 20072
    Prev
    Next
    INDEX
    Explanations

    words related to secure storage or safety

    oai_token-act-pair · gpt-3.5-turbo

    references to "vaults," particularly in contexts related to storage or security

    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
    glers
    -0.94
    atown
    -0.85
    gdala
    -0.84
    cox
    -0.82
    stocks
    -0.79
    erva
    -0.76
    isphere
    -0.75
    TERN
    -0.70
    crow
    -0.68
    ocular
    -0.67
    POSITIVE LOGITS
    eus
    1.03
    lain
    0.99
    ault
    0.94
    aults
    0.91
    ontent
    0.81
    raviolet
    0.81
    atchewan
    0.76
    enture
    0.70
     Dwell
    0.70
    oise
    0.70
    Activations Density 0.028%

    No Known Activations