© 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. 9147
    Prev
    Next
    INDEX
    Explanations

    words related to dependency or reliance

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "rely on"

    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
    ONSORED
    -0.86
    Cola
    -0.82
    Cub
    -0.76
    Brew
    -0.76
    terness
    -0.76
    omsky
    -0.76
    DEN
    -0.75
    MIT
    -0.74
    washer
    -0.72
    arat
    -0.71
    POSITIVE LOGITS
     behalf
    0.87
     scraps
    0.81
     inputs
    0.80
     subsistence
    0.78
     circumst
    0.76
     input
    0.75
     Saturdays
    0.73
     intuition
    0.73
     trusting
    0.72
     unreliable
    0.72
    Activations Density 0.053%

    No Known Activations