© 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. 0-RES-JB
    11. 5303
    Prev
    Next
    INDEX
    Explanations

    words related to connectivity and linking things together

    oai_token-act-pair · gpt-3.5-turbo

    the word "connect" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesty
    -0.72
    mist
    -0.70
    ants
    -0.69
     Rampage
    -0.67
     Mare
    -0.66
    oslov
    -0.65
    resy
    -0.64
     withholding
    -0.63
    eous
    -0.63
     Nightmare
    -0.63
    POSITIVE LOGITS
     connect
    3.46
     connects
    2.33
     connecting
    2.23
    connect
    2.20
     reconnect
    2.01
    Connect
    1.96
     Connect
    1.89
     connected
    1.75
     connection
    1.67
     connections
    1.65
    Activations Density 0.018%

    No Known Activations