© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20632
    Prev
    Next
    INDEX
    Explanations

    words containing a specific sequence of characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific symbol or character within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.80
     mosqu
    -0.71
    theless
    -0.67
     Marble
    -0.67
     detached
    -0.65
    enegger
    -0.64
     shroud
    -0.64
     comprom
    -0.63
    jri
    -0.63
     womb
    -0.63
    POSITIVE LOGITS
    ł
    1.22
    ¹
    1.21
    ª
    1.17
    ij
    1.10
    £
    1.04
    IJ
    1.03
    ı
    1.02
    Ĵ
    1.02
    Ķ
    1.00
    ¤
    0.98
    Activations Density 0.146%

    No Known Activations