© 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. 3-RES-JB
    11. 1546
    Prev
    Next
    INDEX
    Explanations

    terms related to rational thinking or reasoning

    oai_token-act-pair · gpt-3.5-turbo

    references to rationality or logical reasoning

    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
    luster
    -0.82
    ammy
    -0.78
    RAW
    -0.77
     Banner
    -0.75
    hold
    -0.73
    yang
    -0.70
    rael
    -0.70
    HI
    -0.69
    IG
    -0.69
    chin
    -0.69
    POSITIVE LOGITS
    izations
    1.11
    isations
    1.00
    ization
    1.00
    izes
    0.98
    istic
    0.91
    izers
    0.90
    iation
    0.90
    izing
    0.90
    istically
    0.88
    iated
    0.85
    Activations Density 0.007%

    No Known Activations