© 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 EvalsExportsAPI 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. 3500
    Prev
    Next
    INDEX
    Explanations

    complaints or issues related to lack of response or customer service

    oai_token-act-pair · gpt-3.5-turbo

    instances of complaints or grievances related to customer service or support issues

    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
     pioneering
    -0.82
     visionary
    -0.79
     adherents
    -0.79
     charismatic
    -0.78
    Born
    -0.78
     embod
    -0.77
    pires
    -0.76
     synthes
    -0.75
     seminal
    -0.74
     embodied
    -0.73
    POSITIVE LOGITS
     refund
    1.56
     refunds
    1.40
     invoice
    1.23
     emailed
    1.18
     reimb
    1.17
     payment
    1.11
     fax
    1.08
     PayPal
    1.06
     reimbursement
    1.05
     paperwork
    1.04
    Activations Density 0.665%

    No Known Activations