© 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. 10529
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "aid."

    oai_token-act-pair · gpt-3.5-turbo

    references to aid or assistance

    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
    ################
    -0.63
     grill
    -0.60
     Dresden
    -0.59
     bang
    -0.57
     Budapest
    -0.56
     Harlem
    -0.54
    Attach
    -0.53
     Monroe
    -0.52
     Rim
    -0.51
     NIGHT
    -0.51
    POSITIVE LOGITS
    doms
    0.98
    itsch
    0.95
    sie
    0.90
    s
    0.87
    si
    0.82
    oman
    0.81
    t
    0.81
    robe
    0.80
    taker
    0.80
    IUM
    0.80
    Activations Density 0.046%

    No Known Activations