© 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. 23541
    Prev
    Next
    INDEX
    Explanations

    words related to dealing with various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deal" and its variations, indicating a focus on negotiation or management of situations

    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
    antha
    -0.64
    wagen
    -0.63
    roud
    -0.61
    avorite
    -0.58
     reacting
    -0.57
    ilings
    -0.56
    fram
    -0.56
     STATS
    -0.56
    Ħ¢
    -0.56
    jiang
    -0.55
    POSITIVE LOGITS
    UCT
    0.79
     harshly
    0.79
     with
    0.78
    lers
    0.75
    atively
    0.75
     directly
    0.75
    breakers
    0.73
    ison
    0.70
    ptin
    0.70
    ICT
    0.69
    Activations Density 0.058%

    No Known Activations