© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    information related to spending habits and costs, particularly focusing on expenses like shelter and food

    oai_token-act-pair · gpt-3.5-turbo

    financial behaviors and spending patterns related to housing and food

    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
     captcha
    -0.81
     CVE
    -0.78
     Archdemon
    -0.76
    CVE
    -0.75
     Defeat
    -0.72
     bidder
    -0.70
    staking
    -0.68
     Jury
    -0.68
    ername
    -0.65
     reneg
    -0.65
    POSITIVE LOGITS
     groceries
    1.16
     foods
    1.05
     leisure
    1.02
     goods
    1.02
     essentials
    1.00
     cigarettes
    0.98
     food
    0.98
    utterstock
    0.97
     possessions
    0.96
     hobbies
    0.95
    Activations Density 0.428%

    No Known Activations