© 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. 9576
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events happening in a structured or orchestrated manner

    oai_token-act-pair · gpt-3.5-turbo

    passive voice constructions and phrases indicating ongoing or repeated actions

    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
     Sly
    -0.78
     Think
    -0.73
     Venture
    -0.66
     RL
    -0.65
     Lud
    -0.64
     UNIVERS
    -0.64
     LV
    -0.64
     Sketch
    -0.63
     Prophe
    -0.63
     Athletic
    -0.63
    POSITIVE LOGITS
     hampered
    0.95
    entimes
    0.93
     prolifer
    0.92
     facilitated
    0.88
     routinely
    0.87
    ŃĶ
    0.87
     inhibited
    0.86
     undertaken
    0.86
     abound
    0.86
     hindered
    0.86
    Activations Density 0.422%

    No Known Activations