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

    Neuronpedia

    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. 17136
    Prev
    Next
    INDEX
    Explanations

    targets or objectives that someone is focusing on or aiming for

    oai_token-act-pair · gpt-3.5-turbo

    references to aspirations or goals, particularly involving "sights set on" something

    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
    conduct
    -0.92
    period
    -0.76
    stable
    -0.72
    inventoryQuantity
    -0.71
    regate
    -0.67
    prison
    -0.66
    ceed
    -0.64
    ressed
    -0.63
    soType
    -0.63
    required
    -0.63
    POSITIVE LOGITS
     sights
    1.32
    seeing
    1.00
     Sight
    0.85
    ãĤ¤ãĥĪ
    0.85
    ight
    0.79
    peed
    0.77
    terday
    0.69
     attractions
    0.68
    metics
    0.68
    sight
    0.67
    Activations Density 0.011%

    No Known Activations