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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21377
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "ensuring" or "reconfiguring."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consequence and resolution

    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
    è¦ļéĨĴ
    -0.83
    Stone
    -0.72
    icity
    -0.67
    âĨij
    -0.66
    naires
    -0.65
    Beer
    -0.65
    antic
    -0.63
    ikes
    -0.63
    ingham
    -0.61
    iard
    -0.61
    POSITIVE LOGITS
    sembly
    1.21
    nown
    0.96
    vention
    0.95
    metry
    0.92
    merce
    0.89
    kered
    0.87
    querade
    0.86
    quer
    0.86
    nect
    0.86
    figured
    0.84
    Activations Density 0.068%

    No Known Activations