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. 0-RES-JB
    6. 5404
    Prev
    Next
    INDEX
    Explanations

    mentions of ranks or positions within a military context, particularly the term "sergeant."

    oai_token-act-pair · gpt-3.5-turbo

    references to military ranks and roles

    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
     Conver
    -0.78
    Ven
    -0.68
     Disclosure
    -0.67
    itivity
    -0.66
     Sof
    -0.64
     Studio
    -0.64
    nect
    -0.63
     Freak
    -0.63
     Binding
    -0.62
     Jav
    -0.62
    POSITIVE LOGITS
     sergeant
    2.73
     Sergeant
    2.19
     colonel
    2.15
     platoon
    2.09
     regiment
    2.04
     battalion
    1.99
     squadron
    1.79
     Lieutenant
    1.75
     stationed
    1.67
     morale
    1.66
    Activations Density 0.071%

    No Known Activations