INDEX

Explanations

technical terms related to data analysis and scientific methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Efq

-0.84

 Monfieur

-0.79

 myſelf

-0.78

 ſeveral

-0.77

 ſmall

-0.75

 ſta

-0.75

ſelf

-0.74

 reaſon

-0.74

 themſelves

-0.73

 faſt

-0.72

POSITIVE LOGITS

 كمان

0.61

usercontent

0.56

Poster

0.52

poster

0.49

 "..\..\

0.49

Referencer

0.47

 Pristupljeno

0.46

awaiter

0.45

 poster

0.43

יקר

0.43

Activations Density 0.677%

technical terms related to data analysis and scientific methods

No Comments

No Known Activations