© 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. 3-RES-JB
    11. 8402
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pendulum" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "pendulum" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.87
    externalActionCode
    -0.78
    çīĪ
    -0.74
     Marketable
    -0.73
    Downloadha
    -0.72
    ħĭ
    -0.69
    à¦
    -0.69
     Soros
    -0.67
    BILITY
    -0.64
    @@@@
    -0.64
    POSITIVE LOGITS
    ulum
    1.59
    ragon
    1.23
    leton
    1.10
    ennis
    0.92
     Pend
    0.90
    emonium
    0.88
    enza
    0.86
    etry
    0.85
    encing
    0.84
    eter
    0.82
    Activations Density 0.010%

    No Known Activations