© 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. 1-RES-JB
    11. 9395
    Prev
    Next
    INDEX
    Explanations

    phrases related to authoritative positions or commands

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military hierarchy and command

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mob
    -0.84
    ãĤ§
    -0.78
    nation
    -0.73
     Flavoring
    -0.73
    ted
    -0.72
    Network
    -0.72
    Mob
    -0.71
    Eth
    -0.69
    kj
    -0.69
    Rub
    -0.67
    POSITIVE LOGITS
     commanding
    1.26
     commanded
    1.12
     generals
    0.98
     officer
    0.95
     teasp
    0.89
     nomine
    0.88
     commands
    0.88
     officers
    0.86
     colonel
    0.84
     breaths
    0.83
    Activations Density 0.025%

    No Known Activations