© 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. 6-RES-JB
    11. 14682
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or events that are part of a larger context or plan

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote an element of a larger context or part of a whole

    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
    acs
    -0.74
    ozyg
    -0.70
     blat
    -0.67
    liam
    -0.67
     conduc
    -0.66
     butterflies
    -0.65
    worth
    -0.65
    olog
    -0.65
    oor
    -0.64
    nce
    -0.64
    POSITIVE LOGITS
     precaution
    0.78
    lining
    0.77
    interstitial
    0.76
     ongoing
    0.76
     UNESCO
    0.74
     commem
    0.72
     negotiations
    0.69
    iliate
    0.67
     inquiry
    0.67
     [|
    0.66
    Activations Density 0.057%

    No Known Activations