© 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. 5605
    Prev
    Next
    INDEX
    Explanations

    a combination of non-English characters and some English words

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols within text

    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
     Cly
    -0.81
     board
    -0.70
     Perkins
    -0.69
     Tid
    -0.65
     overl
    -0.63
    ographically
    -0.62
     Kens
    -0.62
     Wester
    -0.61
     destiny
    -0.61
     BART
    -0.61
    POSITIVE LOGITS
    ²
    2.23
    Ń
    2.11
    ®
    2.11
    µ
    2.11
    ¬
    2.10
    °
    2.08
    ¹
    2.07
    ¦
    2.06
    ·
    2.03
    ¸
    2.02
    Activations Density 0.006%

    No Known Activations