© 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. 14557
    Prev
    Next
    INDEX
    Explanations

    people's names, including both first and last names

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Charl" or related terms within various contexts

    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
    heimer
    -0.76
    regulated
    -0.75
    raid
    -0.73
    ffic
    -0.73
    ramid
    -0.71
    hower
    -0.69
    HI
    -0.67
    schild
    -0.64
    visor
    -0.63
    ERC
    -0.63
    POSITIVE LOGITS
     Charl
    1.23
    atan
    1.22
    otte
    0.93
    ottesville
    0.90
    otine
    0.86
     pleasures
    0.80
    sburg
    0.80
    otta
    0.79
    eston
    0.79
    ength
    0.78
    Activations Density 0.009%

    No Known Activations