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. 22130
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety precautions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to safety and caution in relation to fire hazards

    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
     Entered
    -0.64
    grain
    -0.62
     colleg
    -0.59
    uscript
    -0.51
     Need
    -0.50
     coral
    -0.49
    jit
    -0.47
     snakes
    -0.47
    uit
    -0.47
    bug
    -0.46
    POSITIVE LOGITS
     namely
    0.97
     albeit
    0.97
     regardless
    0.93
     irrespective
    0.92
     respectively
    0.86
     however
    0.86
     plus
    0.83
     although
    0.83
     huh
    0.79
    thus
    0.79
    Activations Density 0.754%

    No Known Activations