© 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. 7-RES-JB
    11. 1702
    Prev
    Next
    INDEX
    Explanations

    conclusions reached based on investigations or examinations

    oai_token-act-pair · gpt-3.5-turbo

    findings and conclusions related to investigations and evidence assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orns
    -0.84
    anwhile
    -0.77
    rams
    -0.76
    velength
    -0.73
    elight
    -0.72
    tern
    -0.72
     lect
    -0.70
    eatures
    -0.69
     rejoice
    -0.69
     debates
    -0.68
    POSITIVE LOGITS
     probable
    1.23
     credible
    1.02
     wrongdoing
    1.02
     evidence
    0.99
     tampering
    0.93
     improper
    0.92
     negligence
    0.92
     fraudulent
    0.91
     conclusive
    0.91
     misconduct
    0.90
    Activations Density 0.544%

    No Known Activations