© 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. 20091
    Prev
    Next
    INDEX
    Explanations

    words related to rulership, dominance, or control

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "reign" or rule, often in a historical or political context

    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
     Morse
    -0.69
     Stab
    -0.68
    Newsletter
    -0.66
     ``(
    -0.63
    ----------------
    -0.63
     Spac
    -0.59
    Quotes
    -0.58
    Alternatively
    -0.58
    ombies
    -0.58
    Bra
    -0.58
    POSITIVE LOGITS
     reign
    1.29
     tremend
    0.85
     oun
    0.75
    pin
    0.72
    unders
    0.72
    ghai
    0.72
     decree
    0.70
    ieved
    0.70
    ior
    0.69
    æ©
    0.69
    Activations Density 0.008%

    No Known Activations