© 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. 1-RES-JB
    11. 14361
    Prev
    Next
    INDEX
    Explanations

    the word "alpha" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to "alpha" ratings or levels in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.98
    ROR
    -0.87
    ding
    -0.82
    SIGN
    -0.79
    enegger
    -0.78
    ITE
    -0.76
    enance
    -0.75
    ronic
    -0.75
    DM
    -0.74
    vous
    -0.73
    POSITIVE LOGITS
     Centauri
    1.15
     alpha
    1.04
     predator
    0.79
     males
    0.79
     fide
    0.76
     Moroc
    0.75
     predators
    0.75
     male
    0.73
    xual
    0.73
    alpha
    0.73
    Activations Density 0.006%

    No Known Activations