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. 3-RES-JB
    6. 14548
    Prev
    Next
    INDEX
    Explanations

    references to the science fiction horror franchise "Alien."

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Alien" film franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lisher
    -0.84
    theless
    -0.77
    enance
    -0.76
    DCS
    -0.70
    sub
    -0.69
    serving
    -0.68
    heet
    -0.68
    umbn
    -0.67
    ׾
    -0.66
     governing
    -0.66
    POSITIVE LOGITS
     Predator
    1.05
     Alien
    0.97
    Alien
    0.95
     Resurrection
    0.89
     Centauri
    0.86
     Predators
    0.82
    adelphia
    0.81
     Machines
    0.81
    buster
    0.80
     Tracker
    0.80
    Activations Density 0.025%

    No Known Activations