© 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. 11-RES-JB
    11. 11600
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort and achievement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to effort and financial aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicop
    -0.67
     blur
    -0.61
    aucuses
    -0.58
     mascul
    -0.57
    itas
    -0.57
    lag
    -0.57
     mell
    -0.57
    instein
    -0.56
     confusion
    -0.55
    amera
    -0.54
    POSITIVE LOGITS
    selves
    0.77
     upon
    0.76
     entails
    0.75
     Against
    0.67
    pires
    0.66
    edIn
    0.65
     towards
    0.64
    Against
    0.63
     entail
    0.63
    against
    0.62
    Activations Density 0.230%

    No Known Activations