© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11301
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or shared beliefs

    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 @ 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
    aunts
    -0.83
    ansk
    -0.83
    chester
    -0.79
    rams
    -0.79
    thur
    -0.76
    asca
    -0.75
    uv
    -0.74
    href
    -0.74
    gin
    -0.73
    hib
    -0.73
    POSITIVE LOGITS
     consensus
    1.50
    ensus
    0.89
     unanim
    0.88
     unanimous
    0.87
     unanimously
    0.86
     orthodoxy
    0.78
     conclud
    0.77
     opinion
    0.76
     assumption
    0.73
     agreement
    0.73
    Activations Density 0.009%

    No Known Activations