© 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. 3-RES-JB
    11. 10718
    Prev
    Next
    INDEX
    Explanations

    references to the city of Madras (Chennai)

    oai_token-act-pair · gpt-3.5-turbo

    the word "Mad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -1.17
    chnology
    -0.93
     Vaugh
    -0.85
    LECT
    -0.81
    oldown
    -0.79
    kefeller
    -0.78
    ORED
    -0.76
    uberty
    -0.75
    lished
    -0.73
    inventoryQuantity
    -0.72
    POSITIVE LOGITS
    agascar
    0.94
    hya
    0.85
    eline
    0.84
    én
    0.81
    der
    0.81
    ras
    0.78
    oka
    0.77
    rid
    0.77
    mad
    0.77
     Mad
    0.77
    Activations Density 0.008%

    No Known Activations