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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24447
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles related to giving addresses or speeches

    oai_token-act-pair · gpt-3.5-turbo

    references to speeches and addresses given to various audiences

    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
     ILCS
    -0.83
    leys
    -0.70
    nery
    -0.69
    nah
    -0.68
    chrome
    -0.68
    ioxide
    -0.67
     filters
    -0.66
    cin
    -0.66
     haz
    -0.64
     crept
    -0.63
    POSITIVE LOGITS
     delegates
    1.01
     attendees
    0.99
     crowds
    0.97
     audiences
    0.88
     Congress
    0.85
     podium
    0.85
     keynote
    0.85
     listeners
    0.84
     applause
    0.83
     rally
    0.83
    Activations Density 0.251%

    No Known Activations