© 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. 4-RES-JB
    11. 21977
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial or structural reconstruction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to construction and rebuilding efforts

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

    No Comments

    Negative Logits
    ubi
    -0.76
    PLIED
    -0.76
    PIN
    -0.75
    ket
    -0.70
    inki
    -0.67
    baum
    -0.66
    REDACTED
    -0.65
    TW
    -0.63
    915
    -0.62
    ufficient
    -0.60
    POSITIVE LOGITS
    issance
    0.84
    ntil
    0.78
     existing
    0.74
     relic
    0.71
     discredited
    0.70
     streng
    0.70
     mant
    0.69
     reintrodu
    0.68
     facade
    0.67
    undown
    0.65
    Activations Density 0.403%

    No Known Activations