© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4837
    Prev
    Next
    INDEX
    Explanations

    verbs relating to making judgments or decisions

    oai_token-act-pair · gpt-3.5-turbo

    the word "deem" and its variations in various contexts relating to judgments or evaluations

    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
     Sparrow
    -0.67
     Pacers
    -0.66
     Hawks
    -0.64
     Semin
    -0.63
     scrimmage
    -0.63
     session
    -0.63
     Lawn
    -0.62
     Prospect
    -0.62
     Jaguars
    -0.60
     Orn
    -0.60
    POSITIVE LOGITS
    phas
    1.38
     deem
    0.92
    eme
    0.85
    EMP
    0.83
    rences
    0.82
     deems
    0.77
    lessly
    0.76
     fide
    0.76
    geist
    0.74
    FW
    0.74
    Activations Density 0.027%

    No Known Activations