© 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. 1-RES-JB
    11. 14279
    Prev
    Next
    INDEX
    Explanations

    names of people and possibly locations mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LIN
    -0.75
    LINE
    -0.72
    MW
    -0.70
    LAN
    -0.67
    writer
    -0.67
    line
    -0.66
    writers
    -0.66
     Analyst
    -0.65
     reef
    -0.64
    LY
    -0.64
    POSITIVE LOGITS
    gio
    1.13
    itsch
    0.89
    ocular
    0.82
    agn
    0.80
    é¾įå¥ij士
    0.79
    abba
    0.79
    éĹĺ
    0.78
    pheus
    0.78
    ãĤ´ãĥ³
    0.76
    etsy
    0.76
    Activations Density 0.032%

    No Known Activations