© 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. 7-RES-JB
    11. 22941
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people, places, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to roles and actions taken by individuals or groups in authority or decision-making positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fax
    -0.64
    Quote
    -0.63
    statement
    -0.60
     Compass
    -0.57
    pic
    -0.56
    laughs
    -0.56
     diary
    -0.56
    Cub
    -0.56
    plate
    -0.56
     Sakuya
    -0.56
    POSITIVE LOGITS
     themselves
    1.27
     respectively
    1.13
    selves
    1.05
     collectively
    1.04
     specialize
    0.86
     converge
    0.81
     jointly
    0.80
     populate
    0.77
     individually
    0.75
     constitute
    0.74
    Activations Density 0.687%

    No Known Activations