© 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. 14105
    Prev
    Next
    INDEX
    Explanations

    verbs related to proposing or suggesting

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to proposals or suggestions being presented

    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
    apo
    -0.65
     pardon
    -0.59
    BLE
    -0.55
     Returning
    -0.55
    iller
    -0.54
    olla
    -0.54
     guiActiveUnfocused
    -0.54
     Location
    -0.54
    orest
    -0.53
    COLOR
    -0.53
    POSITIVE LOGITS
     forth
    1.63
     together
    1.36
     forward
    1.35
    atively
    0.99
     Forth
    0.97
    together
    0.96
     toget
    0.94
     out
    0.87
     forwards
    0.87
     aside
    0.84
    Activations Density 0.101%

    No Known Activations