© 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. 19679
    Prev
    Next
    INDEX
    Explanations

    phrases related to data storage and operations like writing, reconstructing, and managing data

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to data storage and manipulation

    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
    ansas
    -0.74
    osterone
    -0.69
    */(
    -0.69
    é¾
    -0.68
    marriage
    -0.67
     assassinated
    -0.66
    chall
    -0.66
    married
    -0.66
    breeding
    -0.66
    spoken
    -0.63
    POSITIVE LOGITS
    irtual
    0.90
    itial
    0.79
    itialized
    0.69
     default
    0.68
     Output
    0.67
     (~
    0.66
     Default
    0.65
     plugin
    0.64
    Pixel
    0.64
     API
    0.63
    Activations Density 0.947%

    No Known Activations