© 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. 11-RES-JB
    11. 277
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements issued by individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "statement" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iencies
    -0.70
    oiler
    -0.70
    illions
    -0.63
    skill
    -0.62
    levels
    -0.61
    Mods
    -0.60
    ymes
    -0.60
     menace
    -0.58
    cffffcc
    -0.58
    cephal
    -0.58
    POSITIVE LOGITS
     issued
    1.20
     released
    1.16
     emailed
    1.15
     obtained
    1.05
     accompanying
    1.05
     announcing
    1.01
     posted
    0.96
     Thursday
    0.92
     Wednesday
    0.92
     Tuesday
    0.91
    Activations Density 0.055%

    No Known Activations