© 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. 12519
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting legal or criminal connections

    oai_token-act-pair · gpt-3.5-turbo

    references to connections or relationships in various contexts

    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
    stall
    -0.89
    ipel
    -0.86
    oiler
    -0.77
    inse
    -0.73
    uck
    -0.70
    inen
    -0.70
     ãĤµ
    -0.69
    jew
    -0.69
    oeuv
    -0.68
    orns
    -0.67
    POSITIVE LOGITS
     thereto
    0.91
     dealings
    0.81
    llah
    0.80
     cases
    0.78
     proceedings
    0.73
     laundering
    0.71
     connected
    0.71
     instances
    0.71
     Cases
    0.68
     wrongful
    0.68
    Activations Density 0.023%

    No Known Activations