© 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. 3364
    Prev
    Next
    INDEX
    Explanations

    information about various topics, especially related to statements or news, with the key phrase "About" appearing prominently

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with the word "About."

    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
    ³³³³³³³³³³³³³³³³
    -0.71
    oly
    -0.70
    ³³³³
    -0.68
    ocaly
    -0.68
    ammy
    -0.67
    oled
    -0.65
    oling
    -0.63
    SPONSORED
    -0.63
    apt
    -0.63
    cious
    -0.62
    POSITIVE LOGITS
     About
    0.71
    Story
    0.70
    aleb
    0.70
     simultane
    0.69
     Measures
    0.68
     Policies
    0.65
     Us
    0.65
     demographics
    0.65
     Citation
    0.64
     calib
    0.63
    Activations Density 0.007%

    No Known Activations