© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16971
    Prev
    Next
    INDEX
    Explanations

    phrases related to using certain tools, resources, or information for improvement or specific tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and variations of context usage that imply a specific instruction or guideline

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

    No Comments

    Negative Logits
    iatus
    -0.71
    ufact
    -0.67
    llor
    -0.63
    ijn
    -0.61
    ģĸ
    -0.61
    daughter
    -0.60
     Rodrigo
    -0.60
    én
    -0.60
    udic
    -0.59
    ukemia
    -0.59
    POSITIVE LOGITS
     levers
    0.94
     pseudonym
    0.82
     sparing
    0.77
     tools
    0.75
     metaphors
    0.73
     imagination
    0.72
     pretext
    0.72
     metaphor
    0.72
     brakes
    0.71
     gloves
    0.71
    Activations Density 0.236%

    No Known Activations