© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4131
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses indicating a time-related change or progression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "now."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anyl
    -0.77
     Ibid
    -0.73
    uria
    -0.70
     Written
    -0.63
    adequ
    -0.60
     Contrary
    -0.60
    neg
    -0.58
    ilaterally
    -0.58
    inse
    -0.57
     thereof
    -0.57
    POSITIVE LOGITS
     now
    3.24
    now
    2.19
     NOW
    2.02
     Now
    1.90
    Now
    1.66
     nowadays
    1.60
     presently
    1.58
     currently
    1.55
     today
    1.43
    today
    1.28
    Activations Density 0.073%

    No Known Activations