© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    oai_token-act-pair · gpt-3.5-turbo

    mathematical concepts related to probability and statistics

    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
    gio
    -0.66
     jog
    -0.64
     humid
    -0.60
     salsa
    -0.59
     spills
    -0.59
     slideshow
    -0.59
    rency
    -0.59
     Samar
    -0.59
     activ
    -0.58
    gery
    -0.58
    POSITIVE LOGITS
    \)
    0.96
    \
    0.94
    {\
    0.90
    {
    0.89
    _{
    0.88
    actionDate
    0.85
    }\
    0.84
    align
    0.83
    inline
    0.81
    Dir
    0.80
    Activations Density 0.048%

    No Known Activations