INDEX

Explanations

references to award or recognition in a professional or career context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

تقاوى

-0.64

 חיצוניים

-0.55

tagHelperRunner

-0.52

 समीक्षाएं

-0.51

parseFrom

-0.49

enumi

-0.49

Izvori

-0.48

цезда

-0.47

原始内容存档于

-0.46

vance

-0.46

POSITIVE LOGITS

as

2.14

 sebagai

1.76

 jako

1.45

 ως

1.39

作为

1.39

作為

1.34

sebagai

1.23

 Sebagai

1.22

 као

1.20

 bilang

1.17

Activations Density 0.978%

references to award or recognition in a professional or career context

No Known Activations