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. 21044
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancements and changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to innovative changes in service offerings

    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
    ewitness
    -0.84
     Negro
    -0.83
     negro
    -0.80
     ......
    -0.78
     funer
    -0.76
     recount
    -0.76
     Adolf
    -0.75
     disgrace
    -0.74
     recite
    -0.74
     hyster
    -0.74
    POSITIVE LOGITS
     incentiv
    1.02
     innovate
    0.95
     leveraging
    0.92
     scalable
    0.91
     optimizing
    0.89
     tweaks
    0.88
     APIs
    0.88
     workaround
    0.87
     synerg
    0.87
     synergy
    0.86
    Activations Density 0.972%

    No Known Activations