© 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 EvalsExportsinterp-engineNEWAPI 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. 3341
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases depicting a sense of urgency or critical situations

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding the state or condition of society or the nation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    orem
    -0.73
     Sources
    -0.69
    pez
    -0.68
    enary
    -0.67
     Increases
    -0.67
     Opportun
    -0.67
     quotes
    -0.66
    atives
    -0.64
     warranties
    -0.64
     Benefits
    -0.64
    POSITIVE LOGITS
     undergoing
    1.26
     reeling
    1.24
     littered
    1.23
     riddled
    1.16
     rife
    1.14
     dominated
    1.14
     evolving
    1.14
     divided
    1.11
     saturated
    1.11
     crumbling
    1.10
    Activations Density 0.253%

    No Known Activations