© 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. 0-RES-JB
    11. 9906
    Prev
    Next
    INDEX
    Explanations

    mentions of cost or financial terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cost" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dormant
    -0.65
    susp
    -0.65
     registered
    -0.64
     mark
    -0.64
    pol
    -0.63
     marks
    -0.62
    yk
    -0.62
    itory
    -0.61
    ove
    -0.61
     dominant
    -0.60
    POSITIVE LOGITS
     Cost
    3.83
    Cost
    2.74
     Costs
    2.08
    cost
    1.87
     cost
    1.82
     costs
    1.47
     costing
    1.45
     Price
    1.37
    Price
    1.21
     Benefit
    1.15
    Activations Density 0.017%

    No Known Activations