© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14805
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer networks and encryption

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "to"

    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
    iHUD
    -0.73
     exceptions
    -0.70
    mble
    -0.67
     resemb
    -0.65
    ancies
    -0.62
     testim
    -0.59
    Ĥª
    -0.58
    soDeliveryDate
    -0.58
     outl
    -0.58
     deductions
    -0.57
    POSITIVE LOGITS
    ilet
    1.41
    pping
    0.99
    ffee
    0.97
    ppers
    0.91
    othy
    0.88
    asters
    0.88
    ber
    0.87
    ilers
    0.85
    asted
    0.85
    pped
    0.85
    Activations Density 0.038%

    No Known Activations