© 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. 7-RES-JB
    11. 21077
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of boredom and factors or considerations when making decisions

    oai_token-act-pair · gpt-3.5-turbo

    words related to themes of boredom or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esville
    -0.90
    rosis
    -0.83
    eters
    -0.73
    utable
    -0.72
    esar
    -0.69
    eter
    -0.69
    cies
    -0.67
    nect
    -0.67
    kens
    -0.67
    ned
    -0.67
    POSITIVE LOGITS
    andom
    0.83
    MpServer
    0.76
    atis
    0.74
    skirts
    0.71
    APH
    0.70
    cki
    0.70
     Adin
    0.66
    ources
    0.66
     XIII
    0.64
     mund
    0.63
    Activations Density 0.066%

    No Known Activations