© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13689
    Prev
    Next
    INDEX
    Explanations

    names and surnames, with a higher emphasis on surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or references associated with individuals in the document

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

    No Comments

    Negative Logits
    ruciating
    -0.77
    plates
    -0.71
    ģĸ
    -0.68
    otaur
    -0.68
     glim
    -0.67
    natureconservancy
    -0.65
    istered
    -0.65
     Columb
    -0.64
     Midwest
    -0.64
    ndra
    -0.64
    POSITIVE LOGITS
    rez
    1.01
    quez
    0.94
    ques
    0.88
    alez
    0.87
    ombie
    0.86
    etta
    0.84
    irez
    0.84
    ón
    0.83
    eta
    0.83
    uala
    0.82
    Activations Density 0.009%

    No Known Activations