© 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. 10-RES-JB
    11. 3000
    Prev
    Next
    INDEX
    Explanations

    references to founders or individuals who played key roles in creating various organizations or companies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals who have established or created organizations or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allowances
    -0.68
    ureau
    -0.67
    eneg
    -0.67
     degrading
    -0.62
    assault
    -0.60
    catentry
    -0.59
    Deb
    -0.58
     degrade
    -0.58
    uters
    -0.57
     Ukrain
    -0.57
    POSITIVE LOGITS
    founder
    0.89
     Founders
    0.78
     founder
    0.78
     Markus
    0.77
     Founder
    0.74
     founding
    0.72
     Alexis
    0.70
    INC
    0.69
     emer
    0.69
    hip
    0.68
    Activations Density 0.046%

    No Known Activations