© 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. 10-RES-JB
    6. 8149
    Prev
    Next
    INDEX
    Explanations

    phrases related to power and control

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of 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 @ 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
    ilet
    -0.75
    hazard
    -0.72
    grave
    -0.67
     hereafter
    -0.67
    lict
    -0.67
    ippi
    -0.67
    actly
    -0.66
    erville
    -0.65
     externalToEVAOnly
    -0.65
    bage
    -0.64
    POSITIVE LOGITS
     persuasion
    1.08
     imagination
    1.03
     intuition
    0.90
     instinct
    0.84
     inertia
    0.79
     emotion
    0.78
     inference
    0.76
     anecdote
    0.75
     Habit
    0.74
     gravity
    0.74
    Activations Density 0.123%

    No Known Activations