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. 10-RES-JB
    6. 15230
    Prev
    Next
    INDEX
    Explanations

    terms related to online interactions and transactions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to user interactions and capabilities with applications or platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.76
    fal
    -0.70
    jah
    -0.66
    iferation
    -0.63
    éĹ
    -0.62
    sorry
    -0.60
    ahn
    -0.60
    Too
    -0.60
    wagon
    -0.60
    Defense
    -0.59
    POSITIVE LOGITS
     customized
    1.08
     custom
    0.98
     unlimited
    0.95
     arbitrary
    0.92
     multiple
    0.89
     freely
    0.89
     anonymously
    0.87
     whatever
    0.87
     additional
    0.86
     creations
    0.85
    Activations Density 0.300%

    No Known Activations