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. 23204
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and packing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to packing and moving, especially the act of preparing items for transport

    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
     Spiegel
    -0.72
    phant
    -0.72
     Sutherland
    -0.71
    pher
    -0.68
    ĸļ
    -0.66
    azeera
    -0.65
    pherd
    -0.65
    aterasu
    -0.65
    lander
    -0.64
    iva
    -0.64
    POSITIVE LOGITS
     shelves
    0.93
    pload
    0.91
     Crate
    0.80
     crates
    0.74
     sleeves
    0.74
     groceries
    0.74
    odder
    0.73
     lbs
    0.73
     wagon
    0.70
     lid
    0.70
    Activations Density 0.633%

    No Known Activations