© 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. 775
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    references to specific goals in sports contexts

    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
    OWS
    -0.75
    vette
    -0.70
    abus
    -0.70
    çĦ
    -0.69
    erver
    -0.68
    stocks
    -0.67
    ä¸ī
    -0.67
     Mellon
    -0.66
     jaws
    -0.66
    ragon
    -0.64
    POSITIVE LOGITS
     Messi
    0.82
     Ronaldo
    0.78
    ishly
    0.74
     Ramos
    0.73
    aye
    0.73
    ires
    0.73
     Limbaugh
    0.72
     Barg
    0.71
    zed
    0.69
     Kak
    0.68
    Activations Density 0.035%

    No Known Activations