© 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. 0-RES-JB
    11. 5242
    Prev
    Next
    INDEX
    Explanations

    words related to batteries

    oai_token-act-pair · gpt-3.5-turbo

    references to batteries and their specifications

    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
     Pub
    -0.82
     Ys
    -0.77
    Pub
    -0.75
     Inher
    -0.71
    usercontent
    -0.70
     Shal
    -0.67
     Sche
    -0.67
     Sisters
    -0.67
     pupp
    -0.66
    Cur
    -0.65
    POSITIVE LOGITS
     battery
    3.82
     Battery
    3.14
     batteries
    2.97
    Battery
    2.95
    attery
    1.97
     lithium
    1.79
     charger
    1.43
     electrode
    1.36
     recharge
    1.33
     Lith
    1.29
    Activations Density 0.022%

    No Known Activations