© 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. 0-RES-JB
    11. 16865
    Prev
    Next
    INDEX
    Explanations

    words related to academic subjects such as philosophy, science, and history

    oai_token-act-pair · gpt-3.5-turbo

    references to philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    digit
    -0.74
    Count
    -0.71
    aneously
    -0.68
    ABC
    -0.68
    count
    -0.66
     è£ıè¦ļéĨĴ
    -0.65
    ble
    -0.65
    endez
    -0.64
    OUN
    -0.64
     Reported
    -0.64
    POSITIVE LOGITS
     philosophy
    3.56
     Philosophy
    2.75
     philosophies
    2.69
     philos
    1.98
     philosophers
    1.96
     philosophical
    1.84
     philosopher
    1.76
     theology
    1.73
     philosoph
    1.68
     ethos
    1.68
    Activations Density 0.015%

    No Known Activations