© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 22491
    Prev
    Next
    INDEX
    Explanations

    references to noble houses and political figures in a fantasy setting

    oai_token-act-pair · gpt-3.5-turbo

    key characters and factions involved in power struggles and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.85
    ï¸ı
    -0.81
    taboola
    -0.79
    Recomm
    -0.79
    ï¸
    -0.77
     pestic
    -0.75
    ierrez
    -0.71
    Article
    -0.71
    ļéĨĴ
    -0.70
     sugg
    -0.70
    POSITIVE LOGITS
     Templar
    1.13
     Crusade
    1.07
     Crusader
    1.01
     Dread
    0.97
    canon
    0.96
     Faction
    0.93
     Trooper
    0.92
     Militia
    0.92
     Protector
    0.92
    lords
    0.92
    Activations Density 0.715%

    No Known Activations