© 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. 6-RES-JB
    11. 17784
    Prev
    Next
    INDEX
    Explanations

    names or terms related to nuclear physics

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and terms related to specific individuals or scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HEAD
    -0.72
    XY
    -0.72
    è¦ļéĨĴ
    -0.71
    WAYS
    -0.68
    headers
    -0.67
    head
    -0.65
     Alz
    -0.63
    DOS
    -0.63
     menstrual
    -0.61
    heads
    -0.60
    POSITIVE LOGITS
    eties
    1.00
    ates
    0.99
    į
    0.97
    eness
    0.97
    ±
    0.94
    ophile
    0.93
    ally
    0.93
    ij
    0.93
    ĭ
    0.93
    als
    0.92
    Activations Density 0.040%

    No Known Activations