© 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. 6-RES-JB
    11. 11979
    Prev
    Next
    INDEX
    Explanations

    references to different versions or consoles of a gaming platform

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nintendo Wii U and Xbox One gaming consoles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.81
    -+-+
    -0.78
    rar
    -0.76
    athering
    -0.74
    ãĥ¼ãĤ¯
    -0.72
    ãĤ¹ãĥĪ
    -0.68
    eline
    -0.67
    trump
    -0.66
    pmwiki
    -0.65
    ãĤ©
    -0.64
    POSITIVE LOGITS
    uden
    0.64
     Defender
    0.63
    ®,
    0.62
    âĦ¢
    0.61
     Security
    0.59
     Channel
    0.58
    merce
    0.58
     console
    0.57
    ®
    0.57
     Watch
    0.57
    Activations Density 0.080%

    No Known Activations