© 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. 10-RES-JB
    11. 13712
    Prev
    Next
    INDEX
    Explanations

    mentions of supplies or supporting something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "supply" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
     Warsaw
    -0.64
     burg
    -0.63
     malice
    -0.63
     intimidating
    -0.61
    GER
    -0.61
     betrayal
    -0.60
     Bark
    -0.59
     pivot
    -0.59
     brig
    -0.59
    POSITIVE LOGITS
    ression
    1.47
    orter
    1.45
    osed
    1.43
    ressed
    1.42
    ressive
    1.40
    orters
    1.40
    lication
    1.38
    ressor
    1.37
    ressing
    1.36
    lied
    1.35
    Activations Density 0.016%

    No Known Activations