© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5946
    Prev
    Next
    INDEX
    Explanations

    instances where a comparison is made or something is analyzed for improvement

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "with" and its various contextual uses

    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
    fleet
    -0.73
    assian
    -0.70
    sylvania
    -0.69
    hood
    -0.69
    NN
    -0.68
    icious
    -0.66
    ³³³³³³³³
    -0.65
    SPONSORED
    -0.65
    hari
    -0.65
    iance
    -0.64
    POSITIVE LOGITS
     regards
    2.21
     regard
    2.13
     respect
    1.85
    draw
    1.42
    stood
    1.40
    standing
    1.18
     impunity
    1.17
    holding
    1.14
     hindsight
    1.09
    drawn
    1.07
    Activations Density 0.179%

    No Known Activations