© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 9833
    Prev
    Next
    INDEX
    Explanations

    stylistic characters or symbols, such as accented letters and unusual punctuation

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or symbols within various scripts and languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     board
    -0.79
     favor
    -0.77
     panels
    -0.74
     charm
    -0.71
     overload
    -0.70
     cheer
    -0.67
     representation
    -0.67
     boards
    -0.66
     whistlebl
    -0.65
     delegates
    -0.65
    POSITIVE LOGITS
    ¹
    1.51
    Ń
    1.46
    ª
    1.42
    º
    1.42
    ²
    1.40
    ±
    1.40
    ¨
    1.38
    ¢
    1.38
    ³
    1.37
    £
    1.35
    Activations Density 0.024%

    No Known Activations