© 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. 17585
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistency or consistently performing actions

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "consistently."

    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
    tein
    -0.67
    ster
    -0.62
     Fut
    -0.61
     Ones
    -0.61
     Stuff
    -0.61
     Mour
    -0.61
     possibility
    -0.60
     Kh
    -0.59
    otti
    -0.58
     Mek
    -0.58
    POSITIVE LOGITS
    ãĤ©
    0.83
     evolve
    0.74
     performed
    0.73
     represented
    0.72
     endowed
    0.72
     worshipped
    0.71
     exhibited
    0.71
     priced
    0.70
     outper
    0.70
     accommod
    0.70
    Activations Density 0.067%

    No Known Activations