© 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. 529
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaining or losing control

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating control over a subject or territory

    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
    agher
    -0.87
    urai
    -0.86
    nces
    -0.82
    cellent
    -0.77
    ndra
    -0.73
    offer
    -0.73
    ffer
    -0.72
    yip
    -0.71
    iatus
    -0.71
    rill
    -0.69
    POSITIVE LOGITS
     levers
    0.83
     freeway
    0.74
     reins
    0.74
     perimeter
    0.70
     Territory
    0.69
     metab
    0.68
     controlling
    0.68
     interstate
    0.66
     highways
    0.66
     flora
    0.66
    Activations Density 0.309%

    No Known Activations