© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23160
    Prev
    Next
    INDEX
    Explanations

    mentions of former officials or public figures

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who have held specific prominent positions or titles in government or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acht
    -0.79
    antics
    -0.77
    ñ
    -0.76
    atics
    -0.71
    otle
    -0.69
    anders
    -0.68
    akedown
    -0.66
    TPS
    -0.65
    anche
    -0.64
    plings
    -0.63
    POSITIVE LOGITS
    ly
    0.96
     Former
    0.86
    Former
    0.83
     Yugoslav
    0.76
    Veter
    0.75
     Deputy
    0.71
    ity
    0.71
    mentioned
    0.69
     Vice
    0.69
    theless
    0.68
    Activations Density 0.022%

    No Known Activations