© 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. 10139
    Prev
    Next
    INDEX
    Explanations

    phrases or descriptions indicating physical separation or distance between things or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "separated" 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
    rieg
    -0.72
    lance
    -0.72
    ebus
    -0.71
    erk
    -0.70
    eer
    -0.69
    ledge
    -0.68
    velt
    -0.67
    wr
    -0.65
    onz
    -0.62
    ulz
    -0.60
    POSITIVE LOGITS
     separated
    3.71
    separ
    1.98
     separating
    1.96
     separ
    1.83
     separation
    1.83
     separates
    1.77
     divorced
    1.57
     divided
    1.44
     separate
    1.42
     differentiated
    1.42
    Activations Density 0.024%

    No Known Activations