© 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. 21082
    Prev
    Next
    INDEX
    Explanations

    words related to exerting influence or making demands

    oai_token-act-pair · gpt-3.5-turbo

    references to pressure in societal contexts

    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
    aces
    -0.80
    avior
    -0.76
    BuyableInstoreAndOnline
    -0.76
     Assass
    -0.72
    uration
    -0.71
    utan
    -0.69
     Sham
    -0.69
    onym
    -0.68
    alian
    -0.68
    ammy
    -0.67
    POSITIVE LOGITS
    erous
    0.96
     shoulders
    0.91
     toget
    0.82
     brakes
    0.81
     tyres
    0.78
     exerted
    0.76
     tires
    0.76
     compel
    0.74
    effic
    0.71
     willpower
    0.71
    Activations Density 0.116%

    No Known Activations