© 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. 6-RES-JB
    11. 1029
    Prev
    Next
    INDEX
    Explanations

    phrases listing examples or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    repeated references and the phrase "etc." within the text

    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
    inka
    -0.87
     Lords
    -0.78
    tein
    -0.67
    wives
    -0.65
     Lord
    -0.65
     Fif
    -0.65
    kamp
    -0.63
     parliament
    -0.63
     Rumble
    -0.62
     shadow
    -0.61
    POSITIVE LOGITS
    eter
    1.37
    etc
    1.18
    .,
    1.06
    .?
    1.02
    eteria
    0.95
    uits
    0.92
    ignt
    0.92
    .).
    0.91
    .;
    0.91
     etc
    0.91
    Activations Density 0.018%

    No Known Activations