© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11112
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mod" followed by a number, likely indicating a specific model, concept, or person

    oai_token-act-pair · gpt-3.5-turbo

    references to modular concepts or systems

    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
    éĽ
    -0.83
    FORE
    -0.82
    ģĸ
    -0.82
    çĦ
    -0.77
     Lauder
    -0.76
    éģ
    -0.76
     VIDEOS
    -0.73
    FFFF
    -0.72
    ×Ļ
    -0.71
    é£
    -0.71
    POSITIVE LOGITS
    ules
    1.21
    ifiers
    1.11
    icum
    1.05
    ifier
    1.03
    ifications
    1.00
    ding
    1.00
    ulation
    0.99
    achev
    0.95
    esty
    0.94
    ifying
    0.86
    Activations Density 0.009%

    No Known Activations