© 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. 11-RES-JB
    11. 18815
    Prev
    Next
    INDEX
    Explanations

    words related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific technology and its functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regrets
    -0.80
    livion
    -0.72
     regretted
    -0.71
    notations
    -0.70
    APD
    -0.68
     afterwards
    -0.67
     condol
    -0.66
     thereafter
    -0.65
     adversely
    -0.65
    alyses
    -0.64
    POSITIVE LOGITS
     aptly
    1.04
     Called
    0.91
    named
    0.87
    ensibly
    0.85
    itled
    0.83
     titled
    0.81
     unveiled
    0.79
     Kickstarter
    0.79
     debuted
    0.77
     catchy
    0.77
    Activations Density 0.647%

    No Known Activations