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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23037
    Prev
    Next
    INDEX
    Explanations

    phrases related to traveling to different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating travel or direction

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

    No Comments

    Negative Logits
    need
    -0.75
    natureconservancy
    -0.67
    */(
    -0.67
    pie
    -0.66
     ramifications
    -0.66
     levied
    -0.65
     stru
    -0.65
    attribute
    -0.65
     handled
    -0.64
     payable
    -0.63
    POSITIVE LOGITS
    pload
    0.98
     Disneyland
    0.89
     Liberia
    0.85
    ilet
    0.83
     shore
    0.81
     Omaha
    0.80
     fulfill
    0.80
     relieve
    0.79
     commemorate
    0.79
     visit
    0.79
    Activations Density 0.288%

    No Known Activations