© 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. 0-RES-JB
    11. 4067
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mechanism"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mechanism" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ornings
    -0.89
    hett
    -0.88
    stories
    -0.88
     interviews
    -0.82
    profits
    -0.81
    ographics
    -0.81
    grades
    -0.79
     Chapters
    -0.78
     surveys
    -0.76
     dishes
    -0.75
    POSITIVE LOGITS
     mechanism
    3.26
     procedure
    1.43
     pathway
    1.35
     Mechan
    1.32
     mechanisms
    1.30
     framework
    1.29
     structure
    1.27
     mechanic
    1.25
     solution
    1.24
     arrangement
    1.23
    Activations Density 0.016%

    No Known Activations