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

    Neuronpedia

    Jacobian LensNEW
    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. 3482
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness or capability for a challenge or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of potential or readiness for action

    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
    lein
    -0.72
    irect
    -0.71
    self
    -0.71
    primary
    -0.70
    mys
    -0.64
    Unity
    -0.64
    ãĥĨ
    -0.62
    hiba
    -0.62
    linear
    -0.61
     Advertisement
    -0.61
    POSITIVE LOGITS
     date
    0.98
     speed
    0.97
     scratch
    0.79
     mischief
    0.78
     pace
    0.75
     speeds
    0.73
    cedented
    0.71
     prominence
    0.70
     Speed
    0.69
    date
    0.69
    Activations Density 0.063%

    No Known Activations