© 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. 12-RES-JB
    11. 4356
    Prev
    Next
    INDEX
    Explanations

    the word "full"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to denial or denial of responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.70
    interstitial
    -0.69
    byss
    -0.64
    ibaba
    -0.63
     Outbreak
    -0.63
    ylum
    -0.62
    ainment
    -0.61
    è£ħ
    -0.61
     unfinished
    -0.60
    Ĥª
    -0.60
    POSITIVE LOGITS
     use
    2.10
     uses
    1.86
    use
    1.78
     used
    1.78
     USE
    1.76
     Use
    1.74
    Use
    1.72
     usage
    1.71
    Used
    1.66
     Uses
    1.55
    Activations Density 0.529%

    No Known Activations