© 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. 7-RES-JB
    11. 13505
    Prev
    Next
    INDEX
    Explanations

    phrases related to reusing code across multiple modules

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to software development practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enei
    -0.73
     outlaw
    -0.71
     unlucky
    -0.70
     foul
    -0.70
     obliter
    -0.68
     cartel
    -0.67
     bou
    -0.66
     neigh
    -0.64
     penn
    -0.64
     blight
    -0.64
    POSITIVE LOGITS
     Topics
    1.31
    Introduction
    1.16
    Course
    1.10
    Disclaimer
    1.05
    Python
    1.03
     Instructor
    1.03
    Learning
    1.01
    utorial
    1.01
     topics
    1.00
     Tutorial
    0.99
    Activations Density 0.607%

    No Known Activations