© 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. 4-RES-JB
    11. 7134
    Prev
    Next
    INDEX
    Explanations

    mentions of deliberate or intentional actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to intentionality and purpose

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

    No Comments

    Negative Logits
     Tycoon
    -0.74
     Citation
    -0.73
     Rite
    -0.70
     Warriors
    -0.70
     Parables
    -0.68
    busters
    -0.68
    soon
    -0.67
     Roses
    -0.66
    addons
    -0.65
     Memories
    -0.64
    POSITIVE LOGITS
     planted
    0.83
     plotted
    0.76
     sacrificed
    0.75
     sabot
    0.74
     avoided
    0.73
    ãĤ©
    0.72
    aling
    0.72
     reinvent
    0.72
    designed
    0.72
     designed
    0.72
    Activations Density 0.013%

    No Known Activations