© 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. 4-RES-JB
    11. 9068
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific name "Henrique."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and emotional descriptors related to specific people and places

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

    No Comments

    Negative Logits
    alore
    -0.81
    iful
    -0.77
    wal
    -0.76
    lust
    -0.76
    kat
    -0.75
    ificent
    -0.75
    cus
    -0.75
    raq
    -0.75
    abad
    -0.74
    meal
    -0.74
    POSITIVE LOGITS
     Maya
    0.71
     Salvador
    0.65
    LECT
    0.65
    >>>>>>>>
    0.64
     Gloria
    0.64
    vironment
    0.62
     Schiff
    0.61
    aminer
    0.61
    ean
    0.60
    iosis
    0.60
    Activations Density 0.048%

    No Known Activations