© 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. 16612
    Prev
    Next
    INDEX
    Explanations

    words related to autocracy and political systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political systems and governance, particularly focusing on democratic and autocratic themes

    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
     TF
    -0.67
     fer
    -0.65
     ref
    -0.61
     tagging
    -0.61
     Directions
    -0.61
     needles
    -0.60
     Transport
    -0.60
     transport
    -0.59
     fib
    -0.58
     fle
    -0.58
    POSITIVE LOGITS
    ocracy
    4.33
    ocratic
    4.28
    ocrats
    3.81
    ocrat
    3.80
    ocr
    2.84
    ocrates
    1.67
    archy
    1.33
    ologically
    1.32
    onomy
    1.31
    ocre
    1.25
    Activations Density 0.012%

    No Known Activations