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. 9-RES-JB
    6. 80
    Prev
    Next
    INDEX
    Explanations

    key-value pairs in JSON-like structures

    oai_token-act-pair · gpt-3.5-turbo

    key-value pairs in structured data formats, particularly JSON

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.75
    emetery
    -0.71
    vell
    -0.70
    isconsin
    -0.70
    pez
    -0.69
    orno
    -0.66
    ulty
    -0.66
    é¾įåĸļ士
    -0.66
    resident
    -0.65
    reb
    -0.65
    POSITIVE LOGITS
     null
    1.16
     {"
    1.15
     None
    1.08
     NULL
    1.04
     nil
    1.00
    null
    1.00
     {
    0.97
     false
    0.96
     {}
    0.94
     ['
    0.91
    Activations Density 0.046%

    No Known Activations