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. 16777
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and settings related to software development or customization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to customization and legacy software features

    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
    AIDS
    -0.82
     fortun
    -0.79
    ishops
    -0.77
    arians
    -0.75
    gerald
    -0.75
     charism
    -0.75
    incerity
    -0.74
    ossession
    -0.70
     Armen
    -0.69
    Fest
    -0.69
    POSITIVE LOGITS
     specs
    1.11
     batch
    1.07
     desktop
    1.04
     user
    1.03
     modules
    1.02
     payload
    1.02
     settings
    1.02
     configuration
    1.01
     server
    1.01
     functionality
    1.00
    Activations Density 0.293%

    No Known Activations