© 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. 1-RES-JB
    11. 11233
    Prev
    Next
    INDEX
    Explanations

    religious terms or references

    oai_token-act-pair · gpt-3.5-turbo

    references to belief and believers in a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovely
    -0.68
    NA
    -0.66
    ND
    -0.65
     Paste
    -0.65
     Kardashian
    -0.62
     Occupations
    -0.62
    Accessory
    -0.61
    south
    -0.61
    ebin
    -0.61
     Runner
    -0.61
    POSITIVE LOGITS
    ievers
    1.29
     believer
    1.19
     believers
    1.13
    iever
    0.99
    isSpecialOrderable
    0.93
    ieve
    0.93
    ieving
    0.87
    linger
    0.81
    cius
    0.80
    iosity
    0.79
    Activations Density 0.009%

    No Known Activations