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. 21295
    Prev
    Next
    INDEX
    Explanations

    words related to a specific topic or abbreviation, possibly related to sports or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization, indicated by the term "LSU."

    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
    ãĥĥãĥĪ
    -0.86
    shi
    -0.76
    tained
    -0.64
     Allaah
    -0.63
    cause
    -0.62
    framework
    -0.62
    stroke
    -0.61
     stoked
    -0.59
    oslav
    -0.59
    fare
    -0.58
    POSITIVE LOGITS
    aturday
    1.12
    heed
    1.11
    LS
    0.94
    earch
    0.94
    eeds
    0.92
    aturdays
    0.91
    uable
    0.87
    ensitive
    0.86
    creen
    0.85
    nyder
    0.84
    Activations Density 0.014%

    No Known Activations