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. 5-RES-JB
    6. 16977
    Prev
    Next
    INDEX
    Explanations

    words related to physical movements or actions of traversing from one point to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "across."

    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
    nery
    -0.85
    FORE
    -0.74
    nas
    -0.67
    Parents
    -0.66
     Lauder
    -0.64
    ns
    -0.63
    juven
    -0.61
    anza
    -0.59
    spot
    -0.59
    Loading
    -0.58
    POSITIVE LOGITS
    roads
    1.03
     rooft
    0.93
    atform
    0.91
    urst
    0.79
     paths
    0.77
    cedented
    0.76
    rocal
    0.76
    arrow
    0.73
     platforms
    0.72
    Ĥª
    0.71
    Activations Density 0.027%

    No Known Activations