© 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. 21073
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "pandering" or catering to a specific audience for approval or support

    oai_token-act-pair · gpt-3.5-turbo

    references to "panda" and its variations

    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
     Lauder
    -0.69
     Dakota
    -0.63
    tes
    -0.63
     Crown
    -0.63
     KC
    -0.61
    fully
    -0.58
    FUL
    -0.58
    bound
    -0.58
     Twin
    -0.58
     PARK
    -0.57
    POSITIVE LOGITS
    emonium
    1.58
    emic
    1.51
    ering
    1.33
    erers
    1.29
    emonic
    1.21
    erer
    1.13
    ered
    1.09
    erest
    1.04
    emon
    1.01
    ĸļ
    1.00
    Activations Density 0.062%

    No Known Activations