© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3721
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, particularly wartime actions and consequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the term "Nag" and its variations, likely indicating a focus on the context surrounding it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WIND
    -0.61
     prof
    -0.58
     Neptune
    -0.53
     please
    -0.52
     redistributed
    -0.52
     weekday
    -0.52
    WHERE
    -0.50
     surve
    -0.50
     contraception
    -0.50
    FORMATION
    -0.50
    POSITIVE LOGITS
    orno
    1.34
    asaki
    1.31
    oya
    1.12
    pur
    0.99
    ourney
    0.96
     Hamm
    0.92
    ano
    0.89
    rand
    0.84
    umo
    0.83
    amura
    0.82
    Activations Density 0.017%

    No Known Activations