© 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. 1-RES-JB
    11. 12940
    Prev
    Next
    INDEX
    Explanations

    phrases indicating urgency or importance

    oai_token-act-pair · gpt-3.5-turbo

    words indicating political or controversial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charm
    -0.79
     bung
    -0.71
     pressing
    -0.70
     capsule
    -0.68
    rament
    -0.65
     fame
    -0.63
     charms
    -0.63
     Cerberus
    -0.63
     bunk
    -0.62
     bliss
    -0.62
    POSITIVE LOGITS
    ONSORED
    1.12
    ¡
    0.98
    ¹
    0.98
    £
    0.93
    âĢ
    0.91
    ł
    0.90
    Dialogue
    0.86
    ĺ
    0.85
    į
    0.85
    ¥
    0.83
    Activations Density 0.522%

    No Known Activations