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. 0-RES-JB
    6. 23795
    Prev
    Next
    INDEX
    Explanations

    the verb "gave" followed by a direct object

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "gave."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -0.58
    enz
    -0.57
     BUS
    -0.56
     domestic
    -0.54
     multi
    -0.54
    arak
    -0.53
     oneself
    -0.53
     inline
    -0.52
     international
    -0.52
    uty
    -0.51
    POSITIVE LOGITS
     gave
    3.03
     gives
    1.88
     threw
    1.84
     took
    1.75
     blew
    1.66
     drew
    1.62
     froze
    1.57
     showed
    1.56
     wore
    1.52
     drove
    1.50
    Activations Density 0.011%

    No Known Activations