© 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. 8-RES-JB
    11. 1291
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are being sent somewhere

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.67
     composure
    -0.60
    profit
    -0.60
     concession
    -0.59
    kernel
    -0.58
     advoc
    -0.56
    foundation
    -0.56
     eater
    -0.55
    Enough
    -0.55
     possibilities
    -0.55
    POSITIVE LOGITS
    inel
    1.31
    enced
    1.03
    entious
    1.02
     abroad
    0.92
    irection
    0.87
    imental
    0.85
    encing
    0.81
    encer
    0.80
    opolis
    0.80
    pez
    0.76
    Activations Density 0.043%

    No Known Activations