INDEX

Explanations

occurrences of the word "read" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

Personensuche

-0.45

 vide

-0.42

 video

-0.41

 GBIF

-0.40

 arşivlendi

-0.39

fycat

-0.39

principalColumn

-0.38

 censiti

-0.36

 Video

-0.36

 incon

-0.35

POSITIVE LOGITS

justed

0.90

 aloud

0.90

 comprehension

0.64

 reread

0.58

ioutil

0.58

ying

0.58

unread

0.57

 Comprehension

0.56

Geplaatst

0.55

 读取

0.55

Activations Density 0.159%

occurrences of the word "read" in various contexts

No Comments

No Known Activations

occurrences of the word "read" in various contexts

No Comments

No Known Activations