© 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. 10-RES-JB
    11. 11292
    Prev
    Next
    INDEX
    Explanations

    words related to cold weather and possibly specific names such as "Frost" and "Mann"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters and names associated with a story or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uana
    -0.76
     Leafs
    -0.60
     Sabha
    -0.60
     adv
    -0.59
     SERVICE
    -0.58
    ************
    -0.56
    FORE
    -0.56
     Thai
    -0.56
     Sapphire
    -0.55
    ################
    -0.54
    POSITIVE LOGITS
    heim
    1.00
    sburg
    0.98
    eus
    0.91
    enhagen
    0.89
    esse
    0.88
    iture
    0.88
    enthal
    0.87
    ing
    0.86
    s
    0.85
    enberg
    0.85
    Activations Density 0.123%

    No Known Activations