© 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. 4-RES-JB
    11. 14479
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals "serving as" something or holding a specific position or title

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as" that indicate a role or function

    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
    audi
    -0.65
    oller
    -0.64
    oras
    -0.63
    rol
    -0.62
    rolet
    -0.62
    Sharp
    -0.62
    ron
    -0.62
    LINE
    -0.61
    notice
    -0.61
    ppa
    -0.61
    POSITIVE LOGITS
    pired
    1.02
    pires
    1.01
    bestos
    0.94
    ynchron
    0.92
     well
    0.92
    pire
    0.91
     opposed
    0.87
     follows
    0.85
    criptions
    0.83
     evidenced
    0.81
    Activations Density 0.206%

    No Known Activations