© 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 EvalsExportsinterp-engineNEWAPI 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. 23145
    Prev
    Next
    INDEX
    Explanations

    phrases related to making connections or networks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "connect" and its variations, indicating a focus on networking or connectivity

    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
    cheat
    -0.70
     restraining
    -0.67
    Ħ¢
    -0.65
    fare
    -0.62
    gery
    -0.62
     spoil
    -0.58
    adish
    -0.57
     Ambrose
    -0.57
     Leaves
    -0.56
     subdu
    -0.56
    POSITIVE LOGITS
    icut
    1.34
     dots
    1.24
    ivity
    0.86
     wire
    0.85
    ioned
    0.84
    edin
    0.82
    ions
    0.79
    ibly
    0.78
    links
    0.78
    icative
    0.76
    Activations Density 0.060%

    No Known Activations