© 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. 1-RES-JB
    11. 16139
    Prev
    Next
    INDEX
    Explanations

    sentences that start with specific prepositions like "At", "On", "By", "To", "For", "That", "My", and "Our"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of transition words and phrases that indicate progression or importance in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asonic
    -0.78
    ige
    -0.64
    etsy
    -0.63
    uminati
    -0.63
    dash
    -0.62
    oint
    -0.59
    pine
    -0.58
    microsoft
    -0.57
    Winged
    -0.57
    âĹ¼
    -0.56
    POSITIVE LOGITS
     referen
    0.76
    ĪĴ
    0.72
    cknowled
    0.72
     accur
    0.70
    itialized
    0.69
     simultane
    0.69
     predec
    0.68
     importantly
    0.68
     Costs
    0.67
     citiz
    0.66
    Activations Density 0.694%

    No Known Activations