© 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. 2-RES-JB
    11. 17541
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific entity or concept, "Eraser"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Er" in various contexts

    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
    xual
    -0.85
    creen
    -0.73
    smith
    -0.71
     Parables
    -0.70
    emouth
    -0.69
     Gazette
    -0.69
    erness
    -0.69
    eenth
    -0.68
    ciating
    -0.67
    unct
    -0.65
    POSITIVE LOGITS
    rors
    1.04
    aser
    0.99
    asure
    0.89
    asures
    0.89
    bil
    0.87
    uner
    0.86
     Lauder
    0.85
     Er
    0.82
     Dame
    0.80
    oute
    0.77
    Activations Density 0.007%

    No Known Activations