© 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. 14455
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Ign" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances related to the name "Ignatius."

    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
    borg
    -0.83
    ORGE
    -0.78
    grass
    -0.71
    CHAT
    -0.70
    ------------------------------------------------
    -0.69
    scenes
    -0.64
    mens
    -0.64
    bian
    -0.63
    buster
    -0.61
    76561
    -0.61
    POSITIVE LOGITS
    eous
    1.12
    acio
    1.10
    orable
    1.07
    oreAnd
    1.05
    ance
    0.98
    ition
    0.95
    itability
    0.94
    ibility
    0.94
    omin
    0.94
    ences
    0.93
    Activations Density 0.022%

    No Known Activations