© 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. 11-RES-JB
    11. 18633
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a duration of time or completion of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.84
     Variant
    -0.69
    pict
    -0.65
    Ĭ±
    -0.65
    soType
    -0.64
    ãĥı
    -0.63
    phasis
    -0.63
    IDA
    -0.63
     depended
    -0.63
     Lives
    -0.63
    POSITIVE LOGITS
     arrive
    1.18
     realise
    1.14
     realize
    1.11
     complete
    1.10
     reach
    1.10
     assemble
    1.08
     accumulate
    1.06
     accomplish
    1.04
     finish
    1.03
     resolve
    1.02
    Activations Density 0.123%

    No Known Activations