© 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. 0-RES-JB
    11. 8324
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "Alpha" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of Greek letters or their associated fraternal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gown
    -0.69
    sson
    -0.68
     WTO
    -0.68
     covered
    -0.67
    olkien
    -0.65
     UNESCO
    -0.65
    tty
    -0.65
    arrell
    -0.64
    whel
    -0.63
     Sloven
    -0.63
    POSITIVE LOGITS
     Alpha
    3.90
    Alpha
    3.15
     Beta
    2.45
     alpha
    2.31
     Gamma
    2.31
    alpha
    2.19
    Beta
    2.04
     Omega
    2.00
     Sigma
    1.75
    beta
    1.61
    Activations Density 0.027%

    No Known Activations