© 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. 0-RES-JB
    11. 17984
    Prev
    Next
    INDEX
    Explanations

    phrases related to checking out or confirming something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "checkout" in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Retrieved
    -0.72
     Lastly
    -0.71
    aukee
    -0.70
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.68
     [+
    -0.68
    ©¶æ
    -0.66
     )]
    -0.66
    ļéĨĴ
    -0.66
    IFIED
    -0.64
    roit
    -0.64
    POSITIVE LOGITS
    henko
    0.76
     liner
    0.70
    ello
    0.67
    hen
    0.66
    ament
    0.65
     Fidel
    0.64
     Bulg
    0.64
    heric
    0.63
    omic
    0.63
     Belarus
    0.63
    Activations Density 0.000%

    No Known Activations