© 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. 2-RES-JB
    11. 19709
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Ashton" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    names and references to prominent individuals, particularly those in political or public roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astically
    -0.69
     Domestic
    -0.68
    士
    -0.67
    vernment
    -0.67
     Examiner
    -0.66
    inatory
    -0.65
    ISC
    -0.64
    inally
    -0.62
    ONT
    -0.61
    ãĥ©ãĥ³
    -0.61
    POSITIVE LOGITS
     Kut
    1.58
    rait
    0.89
    asha
    0.87
    alia
    0.87
    raits
    0.86
    ansas
    0.85
    ween
    0.85
    burn
    0.84
    ton
    0.84
    buck
    0.83
    Activations Density 0.006%

    No Known Activations