© 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. 1-RES-JB
    11. 21579
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition or conflict

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conflict or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mental
    -0.81
    edited
    -0.80
    oÄŁ
    -0.79
    mit
    -0.78
    eway
    -0.75
    lys
    -0.75
    pton
    -0.74
    vation
    -0.74
    azing
    -0.74
    mitted
    -0.73
    POSITIVE LOGITS
     pits
    1.46
     pitted
    1.24
     Samson
    0.76
     Jagu
    0.75
     scraps
    0.72
     trenches
    0.70
    naire
    0.69
     stripes
    0.69
    hift
    0.68
    MpServer
    0.68
    Activations Density 0.013%

    No Known Activations