© 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. 6-RES-JB
    11. 2968
    Prev
    Next
    INDEX
    Explanations

    words related to coercion or exerting pressure

    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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahu
    -0.73
    ership
    -0.69
    Story
    -0.68
    NOW
    -0.68
    umer
    -0.67
    mbuds
    -0.67
    ergy
    -0.67
    lus
    -0.66
    aghd
    -0.65
    vironment
    -0.65
    POSITIVE LOGITS
     overtime
    0.81
    otom
    0.80
     laborers
    0.75
     conversions
    0.73
    cible
    0.71
     conformity
    0.70
     concessions
    0.67
     maj
    0.67
     exerted
    0.66
     cooker
    0.66
    Activations Density 0.033%

    No Known Activations