© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    tokens related to the concept of "pledging" or "pledged"

    oai_token-act-pair · gpt-3.5-turbo

    words related to political delegates and their status

    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
     az
    -0.66
     showc
    -0.65
    ansas
    -0.64
     FIRST
    -0.63
     simultane
    -0.62
    addin
    -0.61
    Þ
    -0.60
     whipping
    -0.60
    soDeliveryDate
    -0.60
     airs
    -0.60
    POSITIVE LOGITS
    pling
    1.34
    pled
    1.32
    ĸļ
    1.11
    plet
    1.05
    etooth
    1.05
    ples
    0.95
    ple
    0.94
    peat
    0.93
    xual
    0.86
    hedral
    0.85
    Activations Density 0.016%

    No Known Activations