© 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. 2-RES-JB
    11. 17122
    Prev
    Next
    INDEX
    Explanations

    words related to different types of batteries

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of batteries and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.89
    lihood
    -0.84
    Relations
    -0.81
     Foley
    -0.76
    ctors
    -0.72
    IFA
    -0.72
    published
    -0.72
    VI
    -0.71
    American
    -0.71
    Wilson
    -0.70
    POSITIVE LOGITS
     batteries
    1.24
     battery
    1.00
     recharge
    0.99
     powering
    0.96
     electrodes
    0.93
     charger
    0.88
    attery
    0.87
     capacitor
    0.86
     Battery
    0.86
     storage
    0.84
    Activations Density 0.010%

    No Known Activations