© 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. 2-RES-JB
    11. 15136
    Prev
    Next
    INDEX
    Explanations

    references to the term "gambling" and mentions of the substance "kratom."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gambling and kratom usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duty
    -0.75
     Volt
    -0.71
     AES
    -0.68
     Lac
    -0.64
     lever
    -0.63
    Brand
    -0.62
     lac
    -0.61
     san
    -0.60
     corros
    -0.59
     seat
    -0.59
    POSITIVE LOGITS
    ambling
    1.12
    ithing
    1.07
    merce
    0.90
    heid
    0.86
    rition
    0.84
    elligence
    0.83
    worldly
    0.82
    theless
    0.81
    ithe
    0.80
    doc
    0.79
    Activations Density 0.026%

    No Known Activations