© 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. 10750
    Prev
    Next
    INDEX
    Explanations

    references to royal figures or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to monarchy and royal titles

    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
    pos
    -0.73
    techn
    -0.70
    printf
    -0.69
    vert
    -0.69
    ãĥ£
    -0.67
    fix
    -0.65
    WAR
    -0.65
    roll
    -0.65
    VD
    -0.65
     Nordic
    -0.63
    POSITIVE LOGITS
     Majesty
    1.26
    doms
    1.05
    DOM
    0.90
    conservancy
    0.86
    mares
    0.86
    perty
    0.83
     pard
    0.76
    oice
    0.76
    peror
    0.75
     forbid
    0.74
    Activations Density 0.021%

    No Known Activations