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. 20488
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that involve bringing something or someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of bringing people or things together

    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
     ende
    -0.69
    raid
    -0.65
    Administ
    -0.59
    ording
    -0.58
    é¾įå¥ij士
    -0.58
    ĻĤ
    -0.58
    adelphia
    -0.57
     nomine
    -0.57
    &&
    -0.56
    eme
    -0.56
    POSITIVE LOGITS
    MpServer
    1.01
     closer
    1.00
     onto
    1.00
     forth
    0.98
     into
    0.95
     nearer
    0.92
     attention
    0.86
     back
    0.83
    rawdownloadcloneembedreportprint
    0.80
     awareness
    0.80
    Activations Density 0.166%

    No Known Activations