© 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. 6481
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts, particularly involving rhythm and tempo

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tim" and its variations

    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
    ModLoader
    -0.68
    REDACTED
    -0.68
    Magikarp
    -0.66
    BuyableInstoreAndOnline
    -0.66
    æĸ¹
    -0.65
    ortium
    -0.64
     Jakarta
    -0.63
    naire
    -0.62
     Haram
    -0.61
     Alma
    -0.60
    POSITIVE LOGITS
    othy
    1.40
    estamp
    1.12
    bral
    1.04
    eless
    1.03
    ework
    0.98
    encer
    0.97
    etime
    0.94
    sters
    0.93
    estones
    0.92
    eway
    0.90
    Activations Density 0.011%

    No Known Activations