© 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. 4447
    Prev
    Next
    INDEX
    Explanations

    mentions of financial and material resources being used or acquired

    oai_token-act-pair · gpt-3.5-turbo
    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
    •GPT2 L10 resid: 'LRRRRRLLRRRL'[:-3]

    No Comments

    Negative Logits
    Ĥİ
    -0.98
    £ı
    -0.81
    iatus
    -0.79
    igmatic
    -0.78
    izen
    -0.72
    isode
    -0.71
    ¶ħ
    -0.69
    byter
    -0.69
    ļéĨĴ
    -0.69
    ģĸ
    -0.68
    POSITIVE LOGITS
     resources
    1.40
     manpower
    1.38
     expertise
    1.26
     ammunition
    1.25
     firepower
    1.13
     money
    1.11
     supplies
    1.11
     weaponry
    1.10
     tools
    1.09
     equipment
    1.09
    Activations Density 0.248%

    No Known Activations