© 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. 1-RES-JB
    11. 3500
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the word "Sing"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sing" or its variations, indicating a focus on singing or musical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -1.13
     VICE
    -0.76
    ossession
    -0.73
     hunger
    -0.70
    obbies
    -0.69
    993
    -0.66
    berus
    -0.63
    ooters
    -0.63
    jamin
    -0.62
     Azerb
    -0.60
    POSITIVE LOGITS
    ularity
    1.24
     Sing
    1.21
    Sing
    1.18
    leton
    1.11
    sing
    1.09
    mers
    1.02
    leness
    0.95
    apore
    0.95
    ling
    0.94
    rab
    0.87
    Activations Density 0.002%

    No Known Activations