© 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. 11-RES-JB
    11. 22599
    Prev
    Next
    INDEX
    Explanations

    descriptions and discussions about software and hardware features and updates

    oai_token-act-pair · gpt-3.5-turbo

    features or improvements related to software or product updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    founded
    -0.71
    viol
    -0.70
    arians
    -0.65
    Christian
    -0.65
    stru
    -0.64
    ogens
    -0.64
    politics
    -0.64
    vin
    -0.63
    Whoever
    -0.62
    ought
    -0.62
    POSITIVE LOGITS
     improved
    1.41
     redesigned
    1.36
     revamped
    1.27
     enhanced
    1.19
     Improved
    1.18
     enhancements
    1.13
     customizable
    1.09
     smoother
    1.08
    Improved
    1.08
     improvements
    1.07
    Activations Density 0.390%

    No Known Activations