Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 20225
    Prev
    Next
    INDEX
    Explanations

    phrases related to official visits and meetings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" in various contexts related to visits or trips

    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
    ictive
    -0.86
    rified
    -0.78
    DN
    -0.71
    rils
    -0.69
    ictions
    -0.69
    ministic
    -0.68
    ancial
    -0.67
    ello
    -0.64
     reactions
    -0.64
     implications
    -0.64
    POSITIVE LOGITS
    tnc
    0.86
     Liberia
    0.85
     Disneyland
    0.85
     Dover
    0.77
     meet
    0.76
     visit
    0.75
     Asia
    0.72
     Tours
    0.71
     Mecca
    0.71
     Portsmouth
    0.71
    Activations Density 0.145%

    No Known Activations