© 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. 0-RES-JB
    6. 11308
    Prev
    Next
    INDEX
    Explanations

    words related to categorizing concepts or objects based on a specific characteristic or quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nou
    -0.68
     contained
    -0.63
     Din
    -0.60
    azon
    -0.59
     memorial
    -0.58
     Tomb
    -0.57
    »
    -0.57
    ÑĢ
    -0.56
     adrenaline
    -0.56
     emotion
    -0.56
    POSITIVE LOGITS
    wise
    4.97
     wise
    2.15
    lihood
    1.27
    theless
    1.15
    worldly
    1.09
    rarily
    1.07
     Wise
    0.97
    forward
    0.97
    soever
    0.96
    ardless
    0.95
    Activations Density 0.021%

    No Known Activations