© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    mentions of people in the context of social or political events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate people's actions and feelings

    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
     srfAttach
    -0.94
     predecessor
    -0.79
    berus
    -0.73
     successor
    -0.65
    èĢħ
    -0.64
    Accessory
    -0.63
     Equip
    -0.62
    ãĥ¯
    -0.62
     Reboot
    -0.62
     pupil
    -0.61
    POSITIVE LOGITS
     clam
    0.97
     misunderstand
    0.78
     misinterpret
    0.73
     misunderstanding
    0.71
     wanting
    0.71
     alike
    0.69
     understandably
    0.68
     murm
    0.68
     fooled
    0.67
     grav
    0.67
    Activations Density 0.250%

    No Known Activations