© 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. 11-RES-JB
    11. 3553
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a detailed explanation or discussion

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating explanation or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    nor
    -0.65
    mouth
    -0.63
    oi
    -0.59
     Canaveral
    -0.58
    opped
    -0.57
     canceled
    -0.55
    arov
    -0.54
    mson
    -0.54
    Atl
    -0.54
     Releases
    -0.54
    POSITIVE LOGITS
     below
    1.53
     here
    1.25
     briefly
    1.17
     HERE
    1.15
    below
    1.12
     herein
    1.11
     extensively
    1.10
     hereafter
    1.04
     later
    1.03
     momentarily
    1.01
    Activations Density 0.306%

    No Known Activations