© 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. 4-RES-JB
    11. 22066
    Prev
    Next
    INDEX
    Explanations

    credit-related terms or mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to "credits" in various contexts, particularly in cinema, gaming, and carbon offsets

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

    No Comments

    Negative Logits
    stros
    -0.68
    ife
    -0.67
     advers
    -0.63
    othes
    -0.62
    IFE
    -0.60
    angular
    -0.60
    psy
    -0.60
    istani
    -0.59
     Afgh
    -0.58
    Hur
    -0.58
    POSITIVE LOGITS
     Credits
    0.98
     credits
    0.94
    olor
    0.93
    heet
    0.85
    Credits
    0.83
    redited
    0.81
    urden
    0.78
    enza
    0.77
    ynthesis
    0.75
    ounters
    0.74
    Activations Density 0.009%

    No Known Activations