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

    Neuronpedia

    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. 2-RES-JB
    11. 5555
    Prev
    Next
    INDEX
    Explanations

    content or information that has been thoroughly researched or covered extensively

    oai_token-act-pair · gpt-3.5-turbo

    terms related to thoroughness or extensive research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.74
    jri
    -0.70
    eries
    -0.68
     willingness
    -0.66
    intent
    -0.65
    ties
    -0.65
    utral
    -0.65
    advertising
    -0.64
     believers
    -0.64
    uer
    -0.63
    POSITIVE LOGITS
     researched
    0.85
     extensively
    0.83
     depends
    0.79
     illustrated
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.76
     copied
    0.75
    acebook
    0.74
     utilized
    0.74
     alloc
    0.74
     (>
    0.71
    Activations Density 0.013%

    No Known Activations