Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20754
    Prev
    Next
    INDEX
    Explanations

    words related to time and comparison, such as "today," "now," "more," "less," and "years ago."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various 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
    ERY
    -0.85
    ocrats
    -0.68
    ACY
    -0.66
    osate
    -0.64
    iken
    -0.63
    issions
    -0.62
    ar
    -0.61
    inav
    -0.61
    ESE
    -0.61
    ertodd
    -0.61
    POSITIVE LOGITS
     supposed
    0.86
     wont
    0.86
     today
    0.81
     nowadays
    0.78
     presently
    0.72
     currently
    0.72
     now
    0.70
     accustomed
    0.70
     situated
    0.70
     headquartered
    0.66
    Activations Density 0.137%

    No Known Activations