© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4082
    Prev
    Next
    INDEX
    Explanations

    phrases related to political situations or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that indicate a state of being surrounded or overwhelmed by circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    authors
    -0.71
    OTT
    -0.67
    Ctrl
    -0.67
    include
    -0.66
     Including
    -0.65
    itsu
    -0.64
    minus
    -0.64
    Contact
    -0.64
    isf
    -0.63
    Correct
    -0.63
    POSITIVE LOGITS
     mounting
    1.16
     heightened
    1.15
     escalating
    1.09
     growing
    1.06
     swirling
    1.06
     uproar
    1.05
     turmoil
    1.01
     rumors
    1.01
     speculation
    1.00
     rumours
    1.00
    Activations Density 0.095%

    No Known Activations