© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9064
    Prev
    Next
    INDEX
    Explanations

    phrases related to the debut or premiere of events or media

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "debuted" or related terms indicating the launch of new content

    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
    GO
    -0.78
    oran
    -0.77
    thur
    -0.77
    esthetic
    -0.76
    usal
    -0.74
    ung
    -0.72
    productive
    -0.72
    ne
    -0.71
    acking
    -0.69
    agh
    -0.69
    POSITIVE LOGITS
     debuted
    1.01
     premiered
    0.95
    nesday
    0.94
    éĹĺ
    0.90
    æ©
    0.83
    rities
    0.77
    ãĤ¤ãĥĪ
    0.76
     premie
    0.75
    eatures
    0.74
     misunder
    0.72
    Activations Density 0.004%

    No Known Activations