© 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. 2-RES-JB
    11. 999
    Prev
    Next
    INDEX
    Explanations

    the syllable "Jun"

    oai_token-act-pair · gpt-4-turbo

    dates expressed in the format "Month Day"

    oai_token-act-pair · gpt-3.5-turbo

    dates, specifically referencing the month of June

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.95
     Panic
    -0.73
    Interstitial
    -0.72
     Rift
    -0.68
    ebook
    -0.67
     Trials
    -0.67
     Incarn
    -0.66
    finder
    -0.66
     Fired
    -0.63
     Metatron
    -0.63
    POSITIVE LOGITS
    eteenth
    1.15
    iors
    1.13
     Jun
    1.08
    iper
    1.07
    cture
    1.07
    ctions
    1.01
    jun
    0.97
    Jun
    0.97
    pei
    0.97
    ior
    0.91
    Activations Density 0.004%

    No Known Activations