© 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. 4-RES-JB
    11. 596
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific named locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Il."

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

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.83
    lished
    -0.83
    è¦ļéĨĴ
    -0.81
    ĸļ
    -0.77
     BaseType
    -0.76
    Discussion
    -0.75
    */(
    -0.74
    é¾įå¥ij士
    -0.72
    å£
    -0.70
     CoC
    -0.70
    POSITIVE LOGITS
    ibrary
    1.02
    usions
    0.92
    usive
    0.90
    iber
    0.83
    una
    0.82
    umin
    0.82
    iter
    0.80
    untarily
    0.80
    vl
    0.80
    ugi
    0.79
    Activations Density 0.007%

    No Known Activations