© 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. 11-RES-JB
    11. 337
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring, guaranteeing, or verifying

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.76
    ivated
    -0.72
    insula
    -0.69
    cffffcc
    -0.68
    asse
    -0.67
    Lie
    -0.66
    endar
    -0.65
    ovember
    -0.65
    ovie
    -0.64
    zie
    -0.62
    POSITIVE LOGITS
     that
    1.12
     continuity
    1.03
     fairness
    1.02
     compliance
    0.99
     consistency
    0.98
     adherence
    0.95
     adequate
    0.95
     stability
    0.94
     accuracy
    0.93
     fidelity
    0.93
    Activations Density 0.062%

    No Known Activations