© 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. 8-RES-JB
    11. 3445
    Prev
    Next
    INDEX
    Explanations

    sentences containing explanations or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of explaining situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.73
    iaries
    -0.72
    luster
    -0.70
    mage
    -0.70
    oso
    -0.68
    ngth
    -0.67
    essee
    -0.65
    tackle
    -0.64
    elight
    -0.62
    isha
    -0.62
    POSITIVE LOGITS
     rationale
    1.14
     reasoning
    1.05
     why
    0.92
    why
    0.91
     concepts
    0.90
     virtues
    0.87
     principles
    0.87
     criteria
    0.85
     workings
    0.85
     WHY
    0.85
    Activations Density 0.267%

    No Known Activations