© 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. 3555
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone wanting or requesting something from others

    oai_token-act-pair · gpt-3.5-turbo

    references to desires or requests made by individuals

    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
    ibe
    -0.71
    ggles
    -0.67
    VIDIA
    -0.66
    requires
    -0.62
     srfAttach
    -0.61
    berra
    -0.60
    guyen
    -0.58
    gression
    -0.56
    pite
    -0.55
    ipop
    -0.53
    POSITIVE LOGITS
     to
    1.08
     deported
    0.95
     gone
    0.90
     punished
    0.88
     cleaned
    0.81
     removed
    0.79
    to
    0.79
     prosecuted
    0.79
     silenced
    0.78
     eliminated
    0.77
    Activations Density 0.131%

    No Known Activations