© 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. 17377
    Prev
    Next
    INDEX
    Explanations

    names of people in official or leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference formal titles or positions

    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
    ":"/
    -0.65
     basics
    -0.64
     idols
    -0.62
    zers
    -0.62
    Submit
    -0.62
    rox
    -0.62
    otin
    -0.61
     rive
    -0.61
     exposures
    -0.60
     dirt
    -0.58
    POSITIVE LOGITS
     Mehran
    0.75
     Dmitry
    0.74
    chief
    0.73
    general
    0.72
     overseeing
    0.70
     albeit
    0.70
    vice
    0.69
     Gabriel
    0.68
     Amit
    0.68
     meanwhile
    0.67
    Activations Density 0.202%

    No Known Activations