© 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. 11-RES-JB
    11. 14304
    Prev
    Next
    INDEX
    Explanations

    words related to low-cost or economical solutions

    oai_token-act-pair · gpt-3.5-turbo

    references to low-cost solutions or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XD
    -0.75
     Dull
    -0.71
     Creator
    -0.70
     Brus
    -0.69
     Sandy
    -0.67
     Friends
    -0.66
     pier
    -0.66
     Andromeda
    -0.65
     Remastered
    -0.64
     rewritten
    -0.63
    POSITIVE LOGITS
    income
    1.48
    cost
    1.47
    wage
    1.44
    level
    1.42
    risk
    1.39
    intensity
    1.38
    skilled
    1.36
    budget
    1.36
    profile
    1.34
    margin
    1.33
    Activations Density 0.030%

    No Known Activations