© 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. 6-RES-JB
    11. 1002
    Prev
    Next
    INDEX
    Explanations

    phrases related to lottery activities

    oai_token-act-pair · gpt-3.5-turbo

    references to lottery and gambling contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distingu
    -0.68
    perty
    -0.63
    ctl
    -0.63
    ando
    -0.63
     testim
    -0.63
    iscopal
    -0.63
     deepest
    -0.62
    ç·
    -0.61
    igent
    -0.61
     livest
    -0.60
    POSITIVE LOGITS
    tery
    1.35
    ter
    1.01
    stones
    0.85
    Lot
    0.84
    uses
    0.82
    lights
    0.80
    lighting
    0.78
    creen
    0.76
    tera
    0.76
     Lot
    0.76
    Activations Density 0.027%

    No Known Activations