© 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. 2892
    Prev
    Next
    INDEX
    Explanations

    mentions of things or entities being the same or equal to each other

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating equality or similarity

    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
    glers
    -0.72
    uca
    -0.66
    ãĤ¡
    -0.62
    hiba
    -0.60
    nect
    -0.59
    inas
    -0.58
    ashtra
    -0.57
     ado
    -0.56
    atche
    -0.56
    ort
    -0.56
    POSITIVE LOGITS
     ours
    0.88
     opposed
    0.85
     those
    0.82
     theirs
    0.82
     usual
    0.81
     existed
    0.80
     regards
    0.77
     evidenced
    0.74
     yours
    0.73
     they
    0.72
    Activations Density 0.060%

    No Known Activations