© 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. 11-RES-JB
    11. 6633
    Prev
    Next
    INDEX
    Explanations

    certain groupings of characters that are related to specific symbols or formatting not commonly found in natural language

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the special character 'Ļ'

    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
     decomp
    -0.74
     JPEG
    -0.62
     Newark
    -0.58
     canv
    -0.58
     adm
    -0.57
     misunder
    -0.55
     eclectic
    -0.55
     wedge
    -0.54
     Rhodes
    -0.54
     mushroom
    -0.54
    POSITIVE LOGITS
    s
    1.28
    tion
    1.08
    ï¸ı
    1.01
    til
    1.01
    tis
    1.00
    sis
    0.98
    cause
    0.96
    _.
    0.96
    tions
    0.95
    ti
    0.93
    Activations Density 0.234%

    No Known Activations