© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "jun" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "jun" and its variants, likely focused on the context of time or events related to June

    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
    ocaust
    -0.79
    afe
    -0.65
     Frenzy
    -0.64
     zones
    -0.62
     Bombs
    -0.60
     CTR
    -0.60
     Rage
    -0.60
     Bers
    -0.60
     hol
    -0.60
    ATOR
    -0.59
    POSITIVE LOGITS
    jun
    4.27
    Jun
    1.42
     jun
    1.41
    gee
    0.94
    ihu
    0.93
     Wiley
    0.87
    stem
    0.86
    interstitial
    0.86
    sen
    0.84
    thin
    0.84
    Activations Density 0.048%

    No Known Activations