© 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. 17422
    Prev
    Next
    INDEX
    Explanations

    technical terms related to servers and processors, particularly focusing on aspects related to EPYC processors

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific processor model or product

    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
    auga
    -0.67
    yah
    -0.67
    ````
    -0.65
    iyah
    -0.64
    taboola
    -0.64
     thirds
    -0.64
     à¨
    -0.63
    hips
    -0.62
    folk
    -0.62
    ifiers
    -0.61
    POSITIVE LOGITS
    IC
    1.16
    ICA
    1.09
    IX
    1.06
    IL
    0.99
    HER
    0.98
    TION
    0.94
    ORT
    0.93
    ICS
    0.93
    OSE
    0.93
    hemer
    0.92
    Activations Density 0.025%

    No Known Activations