INDEX

Explanations

terms related to detection processes, particularly in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 whole

-0.74

-0.69

Rcpp

-0.66

tuuri

-0.60

rdd

-0.60

AsUp

-0.59

ribusiness

-0.59

 Whole

-0.59

番

-0.57

whole

-0.57

POSITIVE LOGITS

 Detect

1.99

 detection

1.98

 detect

1.90

 detecting

1.87

 DETECT

1.86

 Detection

1.86

 detected

1.85

 detections

1.82

 Dete

1.81

 DETECTION

1.80

Activations Density 0.091%

terms related to detection processes, particularly in scientific or technical contexts

No Comments

No Known Activations