© 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. 4-RES-JB
    11. 395
    Prev
    Next
    INDEX
    Explanations

    mentions of foreign countries or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to foreign entities or influences

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

    No Comments

    Negative Logits
    illation
    -0.82
     GOODMAN
    -0.81
    byss
    -0.78
    lain
    -0.76
    ividual
    -0.74
    chens
    -0.73
    FUL
    -0.73
    hots
    -0.73
    YR
    -0.72
    ++++
    -0.71
    POSITIVE LOGITS
     affairs
    1.11
     nationals
    1.05
     embassies
    0.86
     Affairs
    0.84
     countries
    0.82
     shores
    0.79
     interference
    0.79
     languages
    0.79
     aid
    0.77
     immunity
    0.76
    Activations Density 0.016%

    No Known Activations