© 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. 15542
    Prev
    Next
    INDEX
    Explanations

    verbs related to exerting control or influence over others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "force" and its variations

    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
    nings
    -0.79
    mbuds
    -0.78
    nown
    -0.73
    vironment
    -0.72
    issance
    -0.72
    thus
    -0.71
     æľ
    -0.68
    amac
    -0.68
    ernels
    -0.68
    available
    -0.67
    POSITIVE LOGITS
     concessions
    0.86
     overtime
    0.85
     closure
    0.83
     conversions
    0.81
     entry
    0.80
     confessions
    0.80
     laborers
    0.79
     compliance
    0.79
     obedience
    0.77
    otom
    0.76
    Activations Density 0.066%

    No Known Activations