© 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. 4-RES-JB
    11. 6554
    Prev
    Next
    INDEX
    Explanations

    opinion pieces or editorials

    oai_token-act-pair · gpt-3.5-turbo

    references to published opinion pieces or editorials

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

    No Comments

    Negative Logits
    aband
    -0.67
    chwitz
    -0.67
    complex
    -0.66
    zik
    -0.65
    prototype
    -0.64
     Rescue
    -0.61
     Rhythm
    -0.61
    skill
    -0.61
     Mk
    -0.61
    artifacts
    -0.60
    POSITIVE LOGITS
     penned
    0.91
     essay
    0.86
     essays
    0.81
     editorial
    0.80
     titled
    0.76
    insula
    0.75
     authored
    0.74
     editor
    0.72
     columnist
    0.72
     excerpts
    0.72
    Activations Density 0.054%

    No Known Activations