© 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. 9-RES-JB
    11. 7369
    Prev
    Next
    INDEX
    Explanations

    instances of passive voice in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of 'being' and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.65
    ilet
    -0.62
     Grass
    -0.62
    vernment
    -0.61
    arta
    -0.60
     Travels
    -0.59
     srfAttach
    -0.59
    \":
    -0.59
    terday
    -0.58
    Buzz
    -0.57
    POSITIVE LOGITS
     exchanged
    1.17
     taken
    1.00
     glean
    0.98
     imposed
    0.96
     given
    0.95
     thrown
    0.95
     handed
    0.95
     bestowed
    0.94
     withheld
    0.93
     achieved
    0.93
    Activations Density 0.229%

    No Known Activations