© 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. 9-RES-JB
    11. 16112
    Prev
    Next
    INDEX
    Explanations

    references to the US Geological Survey

    oai_token-act-pair · gpt-3.5-turbo

    references to government organizations and agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cig
    -0.67
    ï¸
    -0.67
    ijk
    -0.65
    ï¸ı
    -0.64
    lang
    -0.62
    leaf
    -0.61
     Marketable
    -0.61
    java
    -0.59
    ðĿ
    -0.59
    byn
    -0.58
    POSITIVE LOGITS
    onnaissance
    0.84
    assies
    0.74
    psons
    0.72
    itent
    0.72
    orneys
    0.69
     Survey
    0.67
     Veteran
    0.67
     Veterans
    0.67
     Treasury
    0.66
     Postal
    0.66
    Activations Density 0.156%

    No Known Activations