© 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. 9-RES-JB
    11. 13384
    Prev
    Next
    INDEX
    Explanations

    mentions of tents

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "tent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃĽ
    -0.72
     fats
    -0.64
    Grade
    -0.63
     beet
    -0.63
     acron
    -0.60
     Emin
    -0.59
     symmetry
    -0.59
    lda
    -0.58
    metics
    -0.57
    Second
    -0.57
    POSITIVE LOGITS
    atively
    1.42
    acle
    1.37
    pole
    1.20
    acular
    1.14
    acles
    1.07
     encamp
    1.01
    acly
    0.93
     poles
    0.89
    rain
    0.83
    adic
    0.83
    Activations Density 0.060%

    No Known Activations