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. 21209
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to technology products

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to high performance and value in products or services

    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
     juveniles
    -0.85
     antagonists
    -0.81
     pse
    -0.74
     abortions
    -0.72
     surn
    -0.71
     depictions
    -0.69
     derog
    -0.68
     implying
    -0.67
     Reconstruction
    -0.67
     homosexuals
    -0.67
    POSITIVE LOGITS
     hassle
    1.08
     personalized
    0.96
     customize
    0.93
     effortlessly
    0.92
     unforgettable
    0.91
     unbeat
    0.88
     customized
    0.86
     yours
    0.85
    Your
    0.83
     fingertips
    0.83
    Activations Density 0.887%

    No Known Activations