© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7434
    Prev
    Next
    INDEX
    Explanations

    references to a widely held agreement or shared opinion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "consensus" in various contexts

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

    No Comments

    Negative Logits
    hib
    -0.82
    strip
    -0.82
    gin
    -0.79
    chester
    -0.78
    thy
    -0.76
    aunts
    -0.75
    ansk
    -0.74
    gun
    -0.73
    eared
    -0.70
    duc
    -0.69
    POSITIVE LOGITS
     consensus
    1.10
     unanimously
    0.90
    naire
    0.79
    itarian
    0.74
     plank
    0.74
    ensus
    0.74
     amongst
    0.73
     unanim
    0.72
     opinion
    0.71
    IFIED
    0.71
    Activations Density 0.016%

    No Known Activations