© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    the word "universal" regardless of context

    oai_token-act-pair · gpt-4-turbo

    phrases related to the concept of universality

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts or principles that are considered universal

    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
    --------------------------------------------------------
    -0.85
    ritz
    -0.79
    mosp
    -0.74
     Nanto
    -0.73
    Else
    -0.70
     Carbuncle
    -0.70
    ================================================================
    -0.69
    ¯¯¯¯¯¯¯¯
    -0.67
    RAW
    -0.66
    regon
    -0.66
    POSITIVE LOGITS
     universal
    1.01
    ization
    0.97
    ized
    0.95
    universal
    0.91
    isable
    0.88
    izable
    0.86
    isation
    0.86
    ised
    0.84
     acclaim
    0.84
    ITY
    0.81
    Activations Density 0.007%

    No Known Activations