© 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. 1-RES-JB
    11. 22752
    Prev
    Next
    INDEX
    Explanations

    words related to disconnection or separation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to connection and disconnection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GB
    -0.71
    ================
    -0.65
    OPER
    -0.64
     Expend
    -0.63
    Ô
    -0.62
     Cout
    -0.61
     Clancy
    -0.61
    Daily
    -0.58
     Yuan
    -0.58
    TRY
    -0.58
    POSITIVE LOGITS
     disconnect
    1.31
    nect
    1.03
     reconnect
    1.02
    icut
    0.95
    connect
    0.94
    iac
    0.86
     disconnected
    0.84
    ion
    0.82
    icter
    0.81
    connection
    0.80
    Activations Density 0.006%

    No Known Activations