© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23985
    Prev
    Next
    INDEX
    Explanations

    occurrences of the specific name "Mogherini" throughout the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "America" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    down
    -0.77
    affected
    -0.70
    bidden
    -0.70
     vested
    -0.69
    downs
    -0.67
    >>\
    -0.66
    share
    -0.66
    shi
    -0.65
    mire
    -0.64
    legged
    -0.63
    POSITIVE LOGITS
    emia
    1.17
    ica
    1.12
     Rica
    1.01
     Scotia
    0.93
    ahu
    0.89
     Reborn
    0.89
    iah
    0.86
    ican
    0.85
    ption
    0.85
     Juda
    0.84
    Activations Density 0.009%

    No Known Activations