© 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. 8-RES-JB
    11. 7231
    Prev
    Next
    INDEX
    Explanations

    words related to coercion or control, specifically in negative contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coercion or forceful actions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.90
    huge
    -0.78
    ours
    -0.78
    pins
    -0.78
    our
    -0.77
    nings
    -0.77
    warts
    -0.75
    flies
    -0.75
    acular
    -0.74
    =-=-=-=-
    -0.73
    POSITIVE LOGITS
    paren
    0.91
     evaluation
    0.81
     reuse
    0.80
     interrogation
    0.80
     adjud
    0.78
     injection
    0.78
     evaluations
    0.78
     engagement
    0.76
     occupancy
    0.75
     access
    0.74
    Activations Density 0.308%

    No Known Activations