© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3025
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack of information or minimal impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of information or uncertainty

    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
     [|
    -0.68
     unfocusedRange
    -0.64
     SOME
    -0.62
    ĪĴ
    -0.61
     Yin
    -0.59
     widest
    -0.58
     Gate
    -0.58
     Maze
    -0.57
    assadors
    -0.57
    âĺ
    -0.57
    POSITIVE LOGITS
     nor
    0.85
     anymore
    0.81
    pace
    0.74
     survives
    0.74
    matter
    0.72
     whatsoever
    0.71
    verage
    0.70
    nor
    0.69
     trickle
    0.67
    necess
    0.66
    Activations Density 0.192%

    No Known Activations