© 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. 4041
    Prev
    Next
    INDEX
    Explanations

    references to government entities or political topics

    oai_token-act-pair · gpt-3.5-turbo

    references to provincial governance

    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
    Ö¼
    -0.95
    apego
    -0.92
    geist
    -0.89
    chell
    -0.82
    paces
    -0.82
    HO
    -0.81
    adows
    -0.80
    ebus
    -0.79
    schild
    -0.78
    bugs
    -0.77
    POSITIVE LOGITS
     legislatures
    1.09
     provincial
    0.98
     governments
    0.95
     capitals
    0.93
     affairs
    0.90
     province
    0.87
     sovere
    0.86
     councils
    0.85
     provinces
    0.84
     parks
    0.83
    Activations Density 0.006%

    No Known Activations