INDEX

Explanations

terms related to detection and identification processes across various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-0.69

 referenties

-0.67

-0.66

Rcpp

-0.66

tuuri

-0.65

 whole

-0.63

 hora

-0.61

rekli

-0.59

lengths

-0.58

timeScale

-0.58

POSITIVE LOGITS

 Detect

1.52

 Dete

1.48

 DETECT

1.45

 detection

1.41

 detecting

1.38

 detections

1.37

 DETECTION

1.36

 Detectors

1.34

 Detection

1.34

 detectors

1.34

Activations Density 0.119%

terms related to detection and identification processes across various contexts

No Comments

No Known Activations