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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23229
    Prev
    Next
    INDEX
    Explanations

    terms related to power, such as power tools, economic power, political power, power plant, bargain power, nuclear power, and mind-generated power

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "power" in various contexts

    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
    english
    -0.68
    haus
    -0.66
    sey
    -0.65
    itch
    -0.65
    week
    -0.65
    sterdam
    -0.65
    iatrics
    -0.63
    months
    -0.62
    nil
    -0.62
    album
    -0.61
    POSITIVE LOGITS
     power
    3.56
    power
    2.69
     Power
    2.61
    Power
    2.46
     POWER
    2.34
     powers
    2.20
    powers
    1.71
     Powers
    1.62
     electricity
    1.56
     powering
    1.50
    Activations Density 0.031%

    No Known Activations