© 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. 6-RES-JB
    11. 13630
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" in phrases with specific context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "listen to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.87
    recy
    -0.83
    hesion
    -0.72
    widget
    -0.71
    origin
    -0.70
    Delivery
    -0.70
    nir
    -0.70
    oval
    -0.69
    union
    -0.68
    clamation
    -0.68
    POSITIVE LOGITS
     podcasts
    0.90
     voices
    0.85
     music
    0.85
     tapes
    0.84
     hear
    0.84
     audi
    0.83
     Voices
    0.81
     clips
    0.75
     recordings
    0.74
     listen
    0.74
    Activations Density 0.042%

    No Known Activations