© 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. 7-RES-JB
    11. 21108
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Nic"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Nic" or related terms

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.83
    è¦ļéĨĴ
    -0.71
    ãĤ¤ãĥĪ
    -0.69
     Shogun
    -0.68
    LOAD
    -0.68
    ITNESS
    -0.65
    GROUND
    -0.65
     Weinstein
    -0.64
     guiActiveUnfocused
    -0.64
     Cerberus
    -0.61
    POSITIVE LOGITS
    otine
    1.27
    eties
    1.23
    opher
    1.18
    olas
    1.12
    uity
    1.11
    otin
    1.08
    arag
    1.04
    helle
    1.02
    ety
    1.02
    entric
    0.99
    Activations Density 0.026%

    No Known Activations