© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by emotional states

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to individuals and personal relationships

    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
    reach
    -0.77
    athon
    -0.76
    clave
    -0.70
    ML
    -0.68
    shed
    -0.68
    eligible
    -0.68
    ielding
    -0.68
    mire
    -0.67
    grid
    -0.67
    gain
    -0.66
    POSITIVE LOGITS
     Majesty
    1.02
     tides
    0.81
    mos
    0.75
     majesty
    0.74
     salty
    0.73
     charms
    0.70
     fuckin
    0.70
    illac
    0.69
     Vaj
    0.69
    folk
    0.68
    Activations Density 0.485%

    No Known Activations