© 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. 7-RES-JB
    11. 16786
    Prev
    Next
    INDEX
    Explanations

    phrases related to software features or functionalities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating user capabilities or functionalities in applications

    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
    fired
    -0.88
    ĪĴ
    -0.77
     Confeder
    -0.68
    rant
    -0.68
     Worth
    -0.67
     Said
    -0.67
    ylum
    -0.67
     lest
    -0.66
    quickShipAvailable
    -0.66
    president
    -0.64
    POSITIVE LOGITS
     customize
    1.35
     manipulate
    1.22
     navigate
    1.14
     specify
    1.13
     choose
    1.12
     simulate
    1.11
     communicate
    1.11
     visualize
    1.09
     browse
    1.06
     integrate
    1.04
    Activations Density 0.196%

    No Known Activations