© 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. 3-RES-JB
    11. 597
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Catalyst
    -0.68
     replay
    -0.68
     Marketable
    -0.61
     judgment
    -0.61
     misinformation
    -0.61
    lihood
    -0.60
    ++++++++++++++++
    -0.60
    mble
    -0.60
    Journal
    -0.59
     Grateful
    -0.59
    POSITIVE LOGITS
     Poc
    1.10
    oco
    0.98
     Hots
    0.98
    hett
    0.97
    otte
    0.94
    atell
    0.90
    het
    0.87
    rolet
    0.83
    jas
    0.82
    seys
    0.82
    Activations Density 0.006%

    No Known Activations