© 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. 3-RES-JB
    11. 1574
    Prev
    Next
    INDEX
    Explanations

    the word "most" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to the majority or common consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.77
    rompt
    -0.74
     Handling
    -0.67
     CARD
    -0.67
    heid
    -0.65
     Shepherd
    -0.65
     Fist
    -0.62
    icer
    -0.62
    instead
    -0.61
     Films
    -0.60
    POSITIVE LOGITS
     importantly
    0.99
     important
    0.90
    likely
    0.86
    afa
    0.84
     notably
    0.76
     likely
    0.75
     notable
    0.74
     egregious
    0.73
     interesting
    0.71
    interesting
    0.71
    Activations Density 0.084%

    No Known Activations