© 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
    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. 8465
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs and prices

    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
    Not in Any Lists

    No Comments

    Negative Logits
    purpose
    -0.70
     Technique
    -0.68
    ATURE
    -0.67
    ipolar
    -0.66
    erva
    -0.66
    ocent
    -0.65
    Active
    -0.65
     Ago
    -0.65
    beit
    -0.65
    lis
    -0.64
    POSITIVE LOGITS
     prohib
    1.42
     payable
    1.37
     reimb
    1.28
     extortion
    1.26
     reimburse
    1.24
     deductible
    1.23
     incurred
    1.23
     subsid
    1.21
     hefty
    1.21
     skyrocket
    1.18
    Activations Density 0.293%

    No Known Activations