© 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. 9-RES-JB
    11. 3631
    Prev
    Next
    INDEX
    Explanations

    terms related to research and development

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "research" and its variations, indicating a focus on topics related to research and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Remastered
    -0.66
    twitch
    -0.64
    emonic
    -0.62
     Eater
    -0.62
    anza
    -0.62
    veland
    -0.59
     Dud
    -0.58
     Swap
    -0.58
     Brow
    -0.58
    cakes
    -0.57
    POSITIVE LOGITS
     labs
    0.94
     instit
    0.94
     assistants
    0.92
     laboratories
    0.91
     conducted
    0.84
     scientist
    0.84
     institute
    0.83
     undertaken
    0.79
     collaborations
    0.77
     Triangle
    0.77
    Activations Density 0.070%

    No Known Activations