© 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. 2-RES-JB
    11. 2418
    Prev
    Next
    INDEX
    Explanations

    the word "tucked" indicating a hidden or concealed location

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving items being hidden or stored away

    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
    agent
    -0.80
    agents
    -0.72
    idable
    -0.71
     Defenders
    -0.68
    externalActionCode
    -0.64
    ant
    -0.63
    abuse
    -0.62
     Biol
    -0.61
    mentioned
    -0.61
    ance
    -0.60
    POSITIVE LOGITS
     tucked
    1.07
    creen
    0.92
     snug
    0.81
     elbows
    0.78
    userc
    0.77
    nesday
    0.76
     neatly
    0.72
     toget
    0.72
    dden
    0.70
     away
    0.70
    Activations Density 0.024%

    No Known Activations