© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    6. 11243
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ga" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Ortega" or similar names

    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
    payer
    -0.72
    lessly
    -0.69
    iquette
    -0.69
    tle
    -0.67
    tained
    -0.66
     LIFE
    -0.66
    provided
    -0.65
    TY
    -0.65
     Eisenhower
    -0.65
    yll
    -0.64
    POSITIVE LOGITS
    ga
    1.00
    Ga
    0.97
    vernment
    0.89
    ña
    0.87
    ilee
    0.85
    isoft
    0.83
    veyard
    0.80
    ventus
    0.79
    osta
    0.76
    ussian
    0.76
    Activations Density 0.009%

    No Known Activations