© 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. 4-RES-JB
    11. 12178
    Prev
    Next
    INDEX
    Explanations

    phrases that describe a transformation or change of state

    oai_token-act-pair · gpt-3.5-turbo

    instances where something is transformed or changed into a different state or form

    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
    warning
    -0.69
    yright
    -0.68
     Cran
    -0.67
    rella
    -0.65
     toured
    -0.65
    DR
    -0.64
     indeed
    -0.63
    inately
    -0.61
     undertook
    -0.61
     hinted
    -0.60
    POSITIVE LOGITS
     adulthood
    0.87
    ãĤ§
    0.77
     lifelong
    0.69
     unman
    0.68
    pload
    0.67
     mush
    0.67
    displayText
    0.64
    Ò
    0.62
     ashes
    0.62
     usable
    0.61
    Activations Density 0.043%

    No Known Activations