© 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. 9-RES-JB
    11. 20720
    Prev
    Next
    INDEX
    Explanations

    words related to suppression or control

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with control and suppression

    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
    ittal
    -0.91
    çķ
    -0.72
    人
    -0.69
    uben
    -0.68
    format
    -0.66
    olate
    -0.65
    ortality
    -0.64
     Equipment
    -0.63
    oeuv
    -0.63
    olds
    -0.62
    POSITIVE LOGITS
     dissent
    1.32
     dissenting
    1.08
     criticism
    0.99
     rumours
    0.98
     rumors
    0.97
     criticisms
    0.94
     rivals
    0.92
     critics
    0.92
     rebell
    0.91
     doubts
    0.90
    Activations Density 0.230%

    No Known Activations