© 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. 7-RES-JB
    11. 21810
    Prev
    Next
    INDEX
    Explanations

    action verbs related to building, creating, organizing, and arranging

    oai_token-act-pair · gpt-3.5-turbo

    actions related to creation or construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.88
     hampered
    -0.65
     guiActiveUnfocused
    -0.65
     [+]
    -0.64
    ocating
    -0.62
    MAT
    -0.61
    eks
    -0.59
    yond
    -0.59
     berth
    -0.59
    iners
    -0.59
    POSITIVE LOGITS
     himself
    0.80
     herself
    0.80
     copies
    0.69
    otom
    0.65
    ufact
    0.64
    ãĥį
    0.62
    ascript
    0.61
     her
    0.61
    ographs
    0.60
     his
    0.60
    Activations Density 0.463%

    No Known Activations