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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 5803
    Prev
    Next
    INDEX
    Explanations

    years when organizations or companies were founded

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, companies, or entities that were established or created

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.92
     Hazard
    -0.66
    dos
    -0.66
    patch
    -0.65
    Bron
    -0.64
     Hunter
    -0.64
    isite
    -0.64
     Caps
    -0.63
     DOI
    -0.63
    nature
    -0.60
    POSITIVE LOGITS
     founded
    0.85
    ablished
    0.82
    reprene
    0.81
    ãĥ³ãĤ¸
    0.81
    orpor
    0.78
     Seym
    0.76
    ãĤ¢ãĥ«
    0.75
    founded
    0.72
    ulence
    0.71
    smanship
    0.70
    Activations Density 0.017%

    No Known Activations