© 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. 3-RES-JB
    6. 1551
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgments or evaluations of something's worth or validity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being evaluated or judged

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rapp
    -0.67
     Lawn
    -0.66
     scrimmage
    -0.65
     Pacers
    -0.62
    skill
    -0.62
     Semin
    -0.60
     Steelers
    -0.60
     Cheong
    -0.59
     Prospect
    -0.59
     Jaguars
    -0.59
    POSITIVE LOGITS
    phas
    1.29
     deem
    0.92
    rences
    0.79
    geist
    0.79
     fide
    0.76
    omatic
    0.75
    FY
    0.75
    lessly
    0.73
     rul
    0.73
    FW
    0.72
    Activations Density 0.016%

    No Known Activations