© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5127
    Prev
    Next
    INDEX
    Explanations

    related to cost efficiency and pricing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cost-effectiveness and affordability

    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
    dom
    -0.75
    views
    -0.70
     Statements
    -0.62
     Statement
    -0.62
     Survivors
    -0.62
     remarks
    -0.61
    ocy
    -0.61
    onduct
    -0.61
    âĶ
    -0.60
    Åį
    -0.59
    POSITIVE LOGITS
     cheaper
    3.57
     cheapest
    2.41
     cheap
    2.28
     inexpensive
    2.12
     cheaply
    2.01
     pric
    1.94
     pricey
    1.83
     expensive
    1.68
     safer
    1.64
     Cheap
    1.63
    Activations Density 0.015%

    No Known Activations