Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16357
    Prev
    Next
    INDEX
    Explanations

    names related to individuals, specifically ones with the name "Aj" followed by a varying number of characters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and organizations, particularly related to officials and groups

    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
     NXT
    -0.67
     Wolves
    -0.66
     ABV
    -0.65
    hips
    -0.64
     saline
    -0.64
     Fiscal
    -0.61
     paycheck
    -0.60
     IMAGES
    -0.60
     Rangers
    -0.60
     Newfoundland
    -0.60
    POSITIVE LOGITS
    unta
    1.04
     Aj
    0.96
    ahn
    0.92
    ulia
    0.92
    adesh
    0.92
    ibl
    0.92
    ihad
    0.92
    itsu
    0.91
    umar
    0.91
    unction
    0.90
    Activations Density 0.026%

    No Known Activations