© 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. 8-RES-JB
    11. 4560
    Prev
    Next
    INDEX
    Explanations

    phrases related to established norms or traditions

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "conventional" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gur
    -0.75
    olulu
    -0.74
    oning
    -0.68
    interrupted
    -0.68
     Wanted
    -0.68
    hov
    -0.66
    giving
    -0.66
     Allaah
    -0.63
    oÄŁ
    -0.63
     Janeiro
    -0.62
    POSITIVE LOGITS
     wisdom
    1.38
    ization
    0.95
    izations
    0.94
    ties
    0.88
     Warfare
    0.86
    isation
    0.83
    ventional
    0.83
     Wisdom
    0.81
    ised
    0.81
     notions
    0.81
    Activations Density 0.033%

    No Known Activations