© 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. 1-RES-JB
    11. 4886
    Prev
    Next
    INDEX
    Explanations

    phrases related to obtaining or securing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "secured."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahi
    -0.71
    tons
    -0.70
    Kay
    -0.70
    çİĭ
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
    usage
    -0.69
    nia
    -0.68
    price
    -0.68
    INA
    -0.68
    article
    -0.67
    POSITIVE LOGITS
     secured
    1.18
     secure
    1.04
     securing
    0.94
     tremend
    0.91
     Secure
    0.88
     adolesc
    0.85
     millenn
    0.84
    ategory
    0.83
    ĵĺ
    0.83
     mosqu
    0.83
    Activations Density 0.006%

    No Known Activations