© 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. 4-RES-JB
    11. 20774
    Prev
    Next
    INDEX
    Explanations

    the name "Rivers" at varying levels of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rivers" and its variations

    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
    merce
    -0.86
    uckland
    -0.78
    rium
    -0.77
    anooga
    -0.76
    selage
    -0.74
    mble
    -0.72
    iaries
    -0.71
    eared
    -0.70
    ropolitan
    -0.68
    etsy
    -0.67
    POSITIVE LOGITS
    dale
    0.98
    DragonMagazine
    0.89
    cliffe
    0.79
    melon
    0.78
    çīĪ
    0.76
     Rivers
    0.75
     Rivera
    0.75
    ãĥ£
    0.73
    hani
    0.68
     Wiley
    0.68
    Activations Density 0.015%

    No Known Activations