© 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 EvalsExportsAPI 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. 3-RES-JB
    11. 13643
    Prev
    Next
    INDEX
    Explanations

    phrases or sequences of characters preceded by specific symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detached
    -0.73
     guiActiveUnfocused
    -0.72
     bung
    -0.68
     shroud
    -0.67
     obscurity
    -0.67
     Mirage
    -0.66
     dividing
    -0.65
     descending
    -0.65
     division
    -0.65
    creen
    -0.65
    POSITIVE LOGITS
    ł
    1.25
    ¹
    1.14
    ONSORED
    1.07
    IJ
    1.03
    ij
    0.96
    ı
    0.93
    £
    0.91
    Į
    0.90
    ª
    0.90
    Ĵ
    0.89
    Activations Density 0.150%

    No Known Activations