© 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. 2-RES-JB
    11. 5672
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is being introduced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "introduce" 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
    die
    -0.65
    mic
    -0.64
    istic
    -0.60
     fortune
    -0.59
     Myers
    -0.57
    fall
    -0.57
     Sioux
    -0.56
    usal
    -0.56
     solitary
    -0.56
    zees
    -0.55
    POSITIVE LOGITS
     introduce
    1.00
    introdu
    0.96
    urated
    0.92
     introduces
    0.92
     introducing
    0.89
     introduced
    0.85
    Introdu
    0.85
    ounter
    0.76
    ugu
    0.76
     INTO
    0.75
    Activations Density 0.013%

    No Known Activations