© 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. 3-RES-JB
    11. 13625
    Prev
    Next
    INDEX
    Explanations

    words related to power, control, and official positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authority and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovely
    -0.79
    Lens
    -0.76
     Shal
    -0.72
     Taste
    -0.71
     Resist
    -0.69
     Leica
    -0.68
     Sail
    -0.66
     Cure
    -0.65
    xon
    -0.64
    jen
    -0.64
    POSITIVE LOGITS
     authority
    1.19
    Reviewer
    1.08
     nomine
    0.93
     vested
    0.92
     delegated
    0.92
     conferred
    0.89
     confir
    0.89
     figures
    0.84
    ignty
    0.81
     commissions
    0.81
    Activations Density 0.017%

    No Known Activations