© 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. 11-RES-JB
    11. 5397
    Prev
    Next
    INDEX
    Explanations

    terms related to remote control or remote-controlled devices

    oai_token-act-pair · gpt-3.5-turbo

    references to remote-controlled technology and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    VERTISEMENT
    -0.76
    ogh
    -0.69
    uer
    -0.67
    ucc
    -0.66
     Blasio
    -0.65
    uggish
    -0.65
    eny
    -0.65
    ============
    -0.64
    ahead
    -0.64
    trump
    -0.64
    POSITIVE LOGITS
     sensing
    1.21
    controlled
    0.95
     controlled
    0.94
     control
    0.89
    operated
    0.85
     viewing
    0.82
     Controlled
    0.78
     deton
    0.76
    uled
    0.76
     Procedure
    0.71
    Activations Density 0.043%

    No Known Activations