© 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. 11-RES-JB
    11. 24402
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or codes

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to technology and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oké
    -0.56
     sidx
    -0.52
    ecided
    -0.49
     intrigue
    -0.46
    ileaks
    -0.44
    eries
    -0.44
     Canaver
    -0.43
    pedia
    -0.43
    INGS
    -0.43
     intrig
    -0.43
    POSITIVE LOGITS
     prior
    0.49
     contempor
    0.42
    Prior
    0.41
     âī¥
    0.40
     âī¤
    0.40
    pring
    0.40
     âĢ
    0.39
     parity
    0.38
    ÃĤ
    0.38
     higher
    0.38
    Activations Density 1.855%

    No Known Activations