© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    phrases related to prophecies and apocalyptic events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prophecies and apocalyptic themes

    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
    emetery
    -0.91
    sonian
    -0.88
    rador
    -0.85
    ratulations
    -0.79
    Ģ
    -0.76
    ishers
    -0.75
    estone
    -0.75
    keye
    -0.74
    eties
    -0.73
    ª
    -0.73
    POSITIVE LOGITS
     prophecy
    1.22
     prophes
    1.15
     Prophe
    1.10
     Jeremiah
    1.09
     prophe
    1.05
     Ezekiel
    0.99
     prophet
    0.98
    iah
    0.97
     prophets
    0.97
    miah
    0.88
    Activations Density 0.032%

    No Known Activations