© 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. 8-RES-JB
    11. 17868
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreement or majority opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agreement or general acceptance among groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.83
    gin
    -0.81
    strip
    -0.80
    cer
    -0.76
    gun
    -0.76
    gins
    -0.75
    mers
    -0.74
    udi
    -0.74
    ikarp
    -0.73
    zona
    -0.73
    POSITIVE LOGITS
     consensus
    1.01
     opinion
    0.92
     amongst
    0.87
     unanimously
    0.84
     among
    0.82
    ensus
    0.79
    ensical
    0.78
     opinions
    0.77
    atorial
    0.75
     acceptance
    0.74
    Activations Density 0.044%

    No Known Activations