© 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. 8-RES-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    phrases related to desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a desire or motivation to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gart
    -0.71
    laughter
    -0.64
    ONES
    -0.62
    LAN
    -0.61
    summary
    -0.60
    henko
    -0.58
     Manufacturer
    -0.57
     memos
    -0.56
     Juliet
    -0.54
    pause
    -0.54
    POSITIVE LOGITS
     themselves
    0.97
    selves
    0.80
     cov
    0.73
     careers
    0.71
     otherwise
    0.71
     footing
    0.69
     oppressed
    0.69
     menstru
    0.67
     warr
    0.66
    gyn
    0.66
    Activations Density 0.457%

    No Known Activations