© 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. 11723
    Prev
    Next
    INDEX
    Explanations

    positive feedback or comments

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong preferences or ratings

    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
     ÂŃ
    -1.24
    âĢij
    -1.06
    —
    -1.00
    "—
    -0.94
     âĢķ
    -0.85
    ÂŃ
    -0.85
     âĢ
    -0.84
     —
    -0.83
    âĢİ
    -0.80
    ¶
    -0.80
    POSITIVE LOGITS
     alot
    1.57
     didnt
    1.26
     tho
    1.21
     pics
    1.21
     doesnt
    1.20
     english
    1.17
     dont
    1.16
     lvl
    1.16
     lol
    1.10
     haha
    1.09
    Activations Density 1.045%

    No Known Activations