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. 11068
    Prev
    Next
    INDEX
    Explanations

    descriptions of various views or vistas

    oai_token-act-pair · gpt-3.5-turbo

    references to scenic views

    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
    vernment
    -0.88
    vous
    -0.76
     notor
    -0.70
    zzy
    -0.69
     tightening
    -0.67
    ursed
    -0.67
    pmwiki
    -0.67
     surn
    -0.65
    ciating
    -0.65
    encies
    -0.64
    POSITIVE LOGITS
    finder
    1.13
    ports
    1.09
    port
    1.04
    ById
    0.95
    screen
    0.82
    model
    0.80
    points
    0.79
    enery
    0.79
    tower
    0.77
    ults
    0.76
    Activations Density 0.028%

    No Known Activations