INDEX

Explanations

phrases indicating general knowledge or common understanding among people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personendaten

-0.81

typeorm

-0.70

msgTypes

-0.63

MLLoader

-0.63

awtextra

-0.63

rungsseite

-0.62

 صوتيه

-0.61

utilisons

-0.60

databind

-0.59

ειτουργ

-0.59

POSITIVE LOGITS

 obvious

0.57

स्त

0.48

lardır

0.47

 évident

0.47

obvious

0.45

VIOUS

0.45

жере

0.44

 obviously

0.43

 sabemos

0.42

نگار

0.42

Activations Density 0.300%

phrases indicating general knowledge or common understanding among people

No Comments

No Known Activations