© 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. 9-RES-JB
    11. 7225
    Prev
    Next
    INDEX
    Explanations

    instances where comparisons are made involving quantities or levels

    oai_token-act-pair · gpt-3.5-turbo

    references to increased financial expenditures or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.86
    ²¾
    -0.70
    Ń·
    -0.67
    §
    -0.62
    »Ĵ
    -0.61
    ĺħ
    -0.61
    introdu
    -0.61
    completely
    -0.60
    Ļ½
    -0.60
    ģ
    -0.60
    POSITIVE LOGITS
     than
    1.62
     Than
    1.12
    than
    1.00
     money
    0.96
     bang
    0.87
     expensive
    0.83
     dearly
    0.77
     attention
    0.75
     importantly
    0.75
     taxes
    0.73
    Activations Density 0.110%

    No Known Activations