© 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. 6-RES-JB
    11. 17148
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong opinion or directive

    oai_token-act-pair · gpt-3.5-turbo

    the recurring use of a specific symbol or character in various contexts

    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
     decomp
    -0.81
     hob
    -0.69
     Codec
    -0.68
     unmarked
    -0.67
     aid
    -0.66
     shack
    -0.66
     parap
    -0.66
     gib
    -0.65
     filming
    -0.65
     physi
    -0.63
    POSITIVE LOGITS
    ¢
    0.97
    agree
    0.95
    ¬
    0.94
    ı
    0.93
    elong
    0.93
    £
    0.90
    erest
    0.89
    º
    0.87
    ¯
    0.86
    Ĵ
    0.85
    Activations Density 0.396%

    No Known Activations