© 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. 10-RES-JB
    11. 18927
    Prev
    Next
    INDEX
    Explanations

    instances of receiving feedback and complaints

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving feedback or complaints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.72
    raint
    -0.71
    ç¥ŀ
    -0.70
    independence
    -0.68
    istan
    -0.66
    clud
    -0.64
    ibi
    -0.63
    usterity
    -0.62
    antine
    -0.62
    heed
    -0.62
    POSITIVE LOGITS
     requests
    1.75
     inquiries
    1.74
     complaints
    1.64
     queries
    1.55
     enqu
    1.41
     calls
    1.38
     emails
    1.32
     questions
    1.31
     petitions
    1.29
     suggestions
    1.24
    Activations Density 0.296%

    No Known Activations