© 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. 7-RES-JB
    11. 13779
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "ries"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collections or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.89
    Reviewer
    -0.85
    antha
    -0.82
    earable
    -0.82
    nesota
    -0.76
    azine
    -0.74
     meanings
    -0.73
    agonists
    -0.73
    irlf
    -0.71
     guiActiveUn
    -0.71
    POSITIVE LOGITS
    ijn
    0.81
    EF
    0.77
    ijk
    0.74
    ries
    0.74
    enstein
    0.65
    xtap
    0.64
     PRESS
    0.63
    lander
    0.62
    ãĥ¼ãĥ³
    0.62
    UTERS
    0.62
    Activations Density 0.068%

    No Known Activations