© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11222
    Prev
    Next
    INDEX
    Explanations

    URLs starting with "https://"

    oai_token-act-pair · gpt-3.5-turbo

    URLs in the text

    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
     Takeru
    -0.74
     Ori
    -0.74
     Morse
    -0.70
     Adin
    -0.69
     primitive
    -0.66
     utility
    -0.65
     utilities
    -0.64
     synthes
    -0.64
     Lic
    -0.64
     assignments
    -0.63
    POSITIVE LOGITS
    www
    1.26
    twitter
    1.18
    youtu
    1.16
    imgur
    1.14
    goo
    0.97
    ://
    0.97
    archive
    0.94
    think
    0.93
    tw
    0.91
    redd
    0.91
    Activations Density 0.023%

    No Known Activations