© 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. 8-RES-JB
    11. 6309
    Prev
    Next
    INDEX
    Explanations

    names of people or entities called "Max"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Max" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GROUND
    -0.73
    wark
    -0.69
    cipline
    -0.67
    CHO
    -0.64
    selves
    -0.63
    RECT
    -0.62
    FORE
    -0.62
    cemic
    -0.61
    arers
    -0.61
    alam
    -0.59
    POSITIVE LOGITS
    imus
    1.53
    imil
    1.35
    imize
    1.34
    imal
    1.10
    ima
    1.03
    imo
    0.94
    imates
    0.93
    ims
    0.91
     Payne
    0.91
    ime
    0.90
    Activations Density 0.028%

    No Known Activations