© 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. 3-RES-JB
    11. 9179
    Prev
    Next
    INDEX
    Explanations

    terms related to IT systems, logging activities, and data management

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data or informational content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasm
    -0.48
    uthor
    -0.47
     largeDownload
    -0.46
    hin
    -0.44
    CONCLUS
    -0.44
     acknowled
    -0.44
    ploy
    -0.44
    essional
    -0.44
    ħĭ
    -0.43
    orah
    -0.43
    POSITIVE LOGITS
     circa
    0.41
     427
    0.40
     akin
    0.40
     champ
    0.38
     Maxim
    0.38
     1200
    0.38
     Viktor
    0.37
     197
    0.37
     399
    0.37
     eh
    0.36
    Activations Density 5.927%

    No Known Activations