© 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. 6-RES-JB
    6. 291
    Prev
    Next
    INDEX
    Explanations

    the phrase "no one."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "no one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prem
    -0.78
    urations
    -0.65
    tnc
    -0.63
    icer
    -0.62
    ãĥ¯
    -0.62
    etch
    -0.61
    ult
    -0.60
     Labrador
    -0.60
     Lug
    -0.60
    Interstitial
    -0.60
    POSITIVE LOGITS
     else
    1.51
     bothered
    1.00
    Else
    0.89
    else
    0.89
     Else
    0.87
     dime
    0.86
     whatsoever
    0.85
     doubted
    0.84
     cares
    0.83
     cared
    0.79
    Activations Density 0.030%

    No Known Activations