© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20274
    Prev
    Next
    INDEX
    Explanations

    social media posts or online messages

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of written communication, such as blog posts and statements

    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
    cause
    -0.83
    .''.
    -0.69
    $.
    -0.66
    depend
    -0.65
    $$$$
    -0.61
    ').
    -0.61
    /)
    -0.60
    ãĤ¦ãĤ¹
    -0.58
    "},"
    -0.57
    Ingredients
    -0.57
    POSITIVE LOGITS
     titled
    0.89
     published
    0.87
     released
    0.85
     accompanying
    0.83
     dated
    0.81
     announcing
    0.76
     entitled
    0.72
     yesterday
    0.71
     obtained
    0.70
     dubbed
    0.69
    Activations Density 0.164%

    No Known Activations