© 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. 9-RES-JB
    11. 17064
    Prev
    Next
    INDEX
    Explanations

    terms related to reality and truth

    oai_token-act-pair · gpt-3.5-turbo

    references to "reality" and its various implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucky
    -0.89
    edo
    -0.80
    indal
    -0.80
    asus
    -0.78
    oyal
    -0.78
    asso
    -0.78
    atto
    -0.75
    rav
    -0.75
    artney
    -0.75
    oug
    -0.75
    POSITIVE LOGITS
    istically
    0.93
    psons
    0.84
    ignment
    0.83
    ually
    0.83
     TV
    0.79
     Lange
    0.76
     reality
    0.76
     tv
    0.75
     conformity
    0.73
     check
    0.72
    Activations Density 0.038%

    No Known Activations