© 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. 4489
    Prev
    Next
    INDEX
    Explanations

    references to different centuries, particularly the 19th and 20th centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific centuries, particularly the 19th and 20th centuries

    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
    hod
    -0.84
    hing
    -0.78
    chy
    -0.76
    amin
    -0.75
    apa
    -0.73
    subject
    -0.70
    ECTION
    -0.70
    PAC
    -0.70
    iquid
    -0.70
    sites
    -0.69
    POSITIVE LOGITS
    ruary
    0.91
     century
    0.81
     Anniversary
    0.77
    ocene
    0.76
     onwards
    0.76
     Ago
    0.76
     era
    0.75
     onward
    0.74
     BCE
    0.74
     hindsight
    0.72
    Activations Density 0.018%

    No Known Activations