© 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. 9-RES-JB
    11. 17086
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "force" with different intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "force."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    algia
    -0.82
    vironment
    -0.72
    alam
    -0.72
     Hop
    -0.71
    DERR
    -0.69
    STER
    -0.68
    ecause
    -0.67
    eal
    -0.66
    irst
    -0.65
    Accessory
    -0.65
    POSITIVE LOGITS
     maj
    1.35
     multiplier
    1.03
    fulness
    0.98
     exerted
    0.95
    ments
    0.86
     Awakens
    0.85
    ps
    0.82
     force
    0.81
     multipl
    0.81
    vic
    0.80
    Activations Density 0.057%

    No Known Activations