© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15707
    Prev
    Next
    INDEX
    Explanations

    specific mentions of 'detailed' information or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "detailed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aden
    -0.78
    lua
    -0.71
     Wee
    -0.70
    jiang
    -0.67
    qqa
    -0.66
    olean
    -0.65
    avery
    -0.65
     Paw
    -0.64
    weeney
    -0.64
    umar
    -0.64
    POSITIVE LOGITS
     details
    1.03
     detail
    1.00
     descriptions
    1.00
     explanations
    0.88
     outlines
    0.85
     particulars
    0.84
     representations
    0.82
     description
    0.81
     detailing
    0.81
     outline
    0.81
    Activations Density 0.010%

    No Known Activations