© 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. 10137
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer programming or specific technical terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or formatting markers in text

    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
     helicop
    -0.74
     blogging
    -0.70
     tremend
    -0.65
     mosqu
    -0.64
     advertisers
    -0.64
     courts
    -0.62
     eleph
    -0.62
     photograp
    -0.62
     biking
    -0.61
     occas
    -0.60
    POSITIVE LOGITS
    Gameplay
    1.08
    Contents
    1.05
    Appearances
    0.94
    pmwiki
    0.89
    Characters
    0.89
    ãĥ¯ãĥ³
    0.89
    Reward
    0.88
    Synopsis
    0.88
     Edit
    0.87
    Appearance
    0.86
    Activations Density 0.145%

    No Known Activations