© 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. 10-RES-JB
    11. 11440
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "had" and its various forms indicating past actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !'
    -0.77
    !'"
    -0.64
    ?'
    -0.63
    .'
    -0.62
    ?'"
    -0.59
    !!!
    -0.57
     Kills
    -0.56
    .'"
    -0.56
    !!
    -0.56
     Printed
    -0.56
    POSITIVE LOGITS
     "
    1.21
     "...
    1.12
     "'
    1.11
     "âĢ¦
    1.10
     "[
    1.09
     misunderstood
    1.03
     ''
    1.02
     unfairly
    0.93
     "(
    0.92
     deserved
    0.91
    Activations Density 0.380%

    No Known Activations