© 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. 14565
    Prev
    Next
    INDEX
    Explanations

    references to things being revealed or exposed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "revealing" and related contexts

    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
     applied
    -0.64
    otor
    -0.64
    ope
    -0.62
    nea
    -0.61
    capital
    -0.61
     herd
    -0.60
    management
    -0.60
    onder
    -0.59
    etheless
    -0.59
    zone
    -0.58
    POSITIVE LOGITS
     revealing
    0.98
    iary
    0.86
     revelations
    0.82
    rays
    0.79
     disclosures
    0.77
    ly
    0.76
    ively
    0.76
     reveals
    0.75
    ivities
    0.75
    reve
    0.75
    Activations Density 0.008%

    No Known Activations