© 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. 6994
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement or consent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "agreed."

    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
    -0.94
    vantage
    -0.76
    oufl
    -0.75
    undown
    -0.72
    crow
    -0.68
     glands
    -0.67
    agin
    -0.67
    alach
    -0.67
    adish
    -0.65
    \/\/
    -0.65
    POSITIVE LOGITS
     unanimously
    0.98
     thereto
    0.79
     indemn
    0.78
     upon
    0.78
     agreement
    0.76
     pact
    0.75
     agreeing
    0.75
     beforehand
    0.73
     voluntarily
    0.73
     to
    0.72
    Activations Density 0.039%

    No Known Activations