© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 592
    Prev
    Next
    INDEX
    Explanations

    references to time or sequence, focusing on instances of the word "earliest"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "earliest" or initial occurrences in various contexts

    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
    000000
    -0.63
    ah
    -0.57
     anymore
    -0.57
    ort
    -0.55
     Combine
    -0.51
    eur
    -0.51
    bang
    -0.50
    athing
    -0.50
     ¯
    -0.50
    orate
    -0.49
    POSITIVE LOGITS
     earliest
    3.78
     oldest
    1.74
     early
    1.42
     closest
    1.40
     youngest
    1.35
     longest
    1.34
     quickest
    1.32
     shortest
    1.29
     simplest
    1.26
    Early
    1.26
    Activations Density 0.009%

    No Known Activations