© 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. 3388
    Prev
    Next
    INDEX
    Explanations

    terms related to news outlets

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and words related to news and reporting

    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
    lain
    -0.68
    ï¸ı
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    zona
    -0.62
    DEBUG
    -0.57
    LINE
    -0.56
     anecd
    -0.55
     constituent
    -0.55
    DoS
    -0.54
    ashtra
    -0.54
    POSITIVE LOGITS
    angled
    0.90
    eers
    0.80
    phrine
    0.78
    leans
    0.76
    izons
    0.74
     Cinema
    0.72
    aldo
    0.68
    enhagen
    0.67
    ounds
    0.67
    ieties
    0.65
    Activations Density 0.098%

    No Known Activations