Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15990
    Prev
    Next
    INDEX
    Explanations

    government-related terms, especially those related to ministries and departments, specifically with a focus on the Interior and Environment ministries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government ministries and agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cible
    -0.67
     captcha
    -0.63
     ashes
    -0.61
     bunk
    -0.60
    itudes
    -0.58
    916
    -0.58
     nude
    -0.56
     handwriting
    -0.55
     scrimmage
    -0.54
    steen
    -0.54
    POSITIVE LOGITS
     Minister
    1.69
     Secretary
    1.53
     Ministry
    1.42
     Department
    1.35
     minister
    1.32
     secretary
    1.30
     Commissioner
    1.26
     Dept
    1.24
    Secretary
    1.19
     Ministers
    1.14
    Activations Density 0.114%

    No Known Activations