© 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. 1-RES-JB
    11. 22759
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jones" with varying levels of relevance to the surrounding context, as well as numbers associated with the mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jones."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utive
    -0.98
    ãĥŁ
    -0.75
    uated
    -0.73
    aneously
    -0.69
    olitan
    -0.67
    ERAL
    -0.67
    ULAR
    -0.66
    uate
    -0.66
    racted
    -0.66
    ulatory
    -0.65
    POSITIVE LOGITS
     Jones
    1.18
    Jones
    1.16
    sey
    1.09
    boro
    0.99
     Jr
    0.81
    cloth
    0.80
    aqu
    0.80
    hole
    0.79
    mouth
    0.79
    hawk
    0.78
    Activations Density 0.009%

    No Known Activations