© 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. 2-RES-JB
    6. 4138
    Prev
    Next
    INDEX
    Explanations

    characters represented by specific Unicode symbols

    oai_token-act-pair · gpt-3.5-turbo

    special symbols or characters, particularly variations of 'Ħ' and other similar glyphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geries
    -1.04
     foreground
    -0.78
    raints
    -0.77
     distracted
    -0.73
     background
    -0.72
     intrigue
    -0.71
     readiness
    -0.70
     distracting
    -0.70
    gery
    -0.69
     intrig
    -0.69
    POSITIVE LOGITS
    Ħ
    1.26
    и
    1.12
    ij
    1.10
    ļ
    1.08
    ł
    1.05
    ¸
    1.04
    Ĺ
    1.04
    ¼
    1.00
    ¶
    0.99
    ¾
    0.99
    Activations Density 0.003%

    No Known Activations