© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22313
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision making, planning, and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Args
    -0.70
     Upper
    -0.68
     Albion
    -0.64
     Caller
    -0.64
     enthusi
    -0.62
    Late
    -0.62
    grain
    -0.60
     Brist
    -0.60
    VG
    -0.59
    cedented
    -0.59
    POSITIVE LOGITS
     create
    1.17
     expel
    1.10
     declare
    1.09
     withdraw
    1.08
     perform
    1.07
     earn
    1.07
     marry
    1.07
     participate
    1.05
     make
    1.05
     impose
    1.04
    Activations Density 0.441%

    No Known Activations